CN109842817A - The methods, devices and systems of association analysis Video Key content - Google Patents
The methods, devices and systems of association analysis Video Key content Download PDFInfo
- Publication number
- CN109842817A CN109842817A CN201711219871.2A CN201711219871A CN109842817A CN 109842817 A CN109842817 A CN 109842817A CN 201711219871 A CN201711219871 A CN 201711219871A CN 109842817 A CN109842817 A CN 109842817A
- Authority
- CN
- China
- Prior art keywords
- client
- commodity
- video
- emphasis
- close attention
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The present disclosure discloses a kind of methods, devices and systems of association analysis Video Key content, are related to Internet of Things intelligent video application field.This method comprises: obtaining multiple video contents;Structured analysis is carried out to each video content, determines the client in each video content and commodity object information;The emphasis commodity paid close attention to by client in each video content are determined based on the weighting dimension of client and commodity;Interception includes the video clip for the emphasis commodity paid close attention to by client, and links to video clip.The disclosure is linked into all key contents of complete video expression client's focal point commodity, improves the effective information of video content, subsequent manager is facilitated to browse, check, compare and analyze.
Description
Technical field
This disclosure relates to Internet of Things intelligent video application field more particularly to a kind of side of association analysis Video Key content
Method, device and system.
Background technique
The market passenger flow of intelligent video is applied than wide at present, and market manager wishes to obtain by intelligent use more
Valuable information.But in the prior art, intelligent use checks that needing to choose video file when video in advance carries out large-size screen monitors broadcasting,
That is one group of video recording synchronized playback, but video content onrelevant degree, therefore, the effective information that manager obtains are very limited.
Summary of the invention
The disclosure technical problem to be solved is to provide a kind of method of association analysis Video Key content, dress
It sets and system, can be improved monitor video effective information.
On the one hand according to the disclosure, a kind of method for proposing association analysis Video Key content, comprising: obtain multiple videos
Content;Structured analysis is carried out to each video content, determines the client in each video content and commodity object information;Based on client
The emphasis commodity paid close attention to by client in each video content are determined with the weighting dimension of commodity;Interception includes the weight paid close attention to by client
The video clip of point commodity, and video clip is linked.
Optionally, this method further include: direction is paid close attention to by passenger flow Camera Positioning client stop place and client;
Based on client stop place at a distance from commodity and client pays close attention to the weighting dimension in direction and commodity direction and determines each view
The emphasis commodity paid close attention to by client in frequency content.
Optionally, obtain weighting coefficient A and client of the client stop place at a distance from commodity pay close attention to direction with
The weighting coefficient B in commodity direction;Determine that the weighting of client and commodity is tieed up based on the distance parameter and directioin parameter of client and commodity
Degree, wherein distance parameter is client stop place at a distance from commodity and the product of weighting coefficient A, directioin parameter are client's weight
The product of the angle and weighting coefficient B in point concern direction and commodity direction;If the weighting dimension of client and commodity is greater than weighting dimension
Spend threshold value, it is determined that commodity are the emphasis commodity paid close attention to by client in video content.
Optionally, this method further include: client's residence time information is obtained by passenger flow video camera;Based on client stop place
It sets and marks in each video content with the video at time point with client's residence time as index segment.
Optionally, the image information for the emphasis commodity paid close attention to by client is extracted, and marks key frame;It is intercepted based on key frame
Comprising the video clip for the emphasis commodity paid close attention to by client in each video clip;It is chronologically-based respectively in each video content
The video clip of client's emphasis commodity of interest links;Or client in each video content in same time point is closed
The video clip of the emphasis commodity of note is linked.
Optionally, this method further include: the video clip of link being sent to client, being broadcast with will pass through client concentration
Put the emphasis commodity video information comprising being paid close attention to by client.
According to another aspect of the present disclosure, it is also proposed that a kind of device of association analysis Video Key content, comprising: video obtains
Unit is taken, for obtaining multiple video contents;Structured analysis unit, for carrying out structured analysis to each video content, really
Client and commodity object information in fixed each video content;Emphasis commodity determination unit, for the weighting based on client and commodity
Dimension determines the emphasis commodity paid close attention to by client in each video content;Video clip interception unit, for intercepting comprising objective
The video clip of the emphasis commodity of family concern;Video clip link unit, for being linked to video clip.
Optionally, the device further include: customer information acquiring unit, for passing through passenger flow Camera Positioning client stop place
Set and stop directional information;Emphasis commodity determination unit be used for based on client stop place at a distance from commodity and client weight
The weighting dimension in point concern direction and commodity direction determines the emphasis commodity paid close attention to by client in each video content.
Optionally, emphasis commodity determination unit be also used to obtain weighting coefficient A of the client stop place at a distance from commodity,
And client pays close attention to the weighting coefficient B in direction Yu commodity direction;Distance parameter and directioin parameter based on client and commodity
Determine the weighting dimension of client and commodity, wherein distance parameter is for client stop place with weighting coefficient A's at a distance from commodity
Product, directioin parameter are that client pays close attention to the angle in direction and commodity direction and the product of weighting coefficient B;If client and commodity
Weighting dimension be greater than weighting dimension threshold value, it is determined that commodity be video content in by client pay close attention to emphasis commodity.
Optionally, the device further include: index segment determination unit, when for being resident based on client stop place and client
Between mark in each video content with time point video as index segment;Wherein, customer information acquiring unit is also used to lead to
It crosses passenger flow video camera and obtains client's residence time information.
Optionally, video clip interception unit is used to extract the image information for the emphasis commodity paid close attention to by client, and marks
Key frame is intercepted in each video clip based on key frame comprising the video clip for the emphasis commodity paid close attention to by client;Video clip
Video clip of the link unit for chronologically-based emphasis commodity of interest to client in each video content respectively carries out
Link, or the video clip of the emphasis commodity of interest of client in each video content in same time point is linked.
Optionally, the device further include: video transmission unit, for the video clip of link to be sent to client, with
It will pass through client concentration and play the emphasis commodity video information comprising being paid close attention to by client.
According to another aspect of the present disclosure, it is also proposed that a kind of system of association analysis Video Key content, including commodity are taken the photograph
Camera, passenger flow video camera, client and above-mentioned association analysis Video Key content device.
According to another aspect of the present disclosure, it is also proposed that a kind of device of association analysis Video Key content, comprising: storage
Device;And it is coupled to the processor of memory, processor is configured as example above-mentioned based on the instruction execution for being stored in memory
Method.
According to another aspect of the present disclosure, it is also proposed that a kind of computer readable storage medium is stored thereon with computer journey
The step of sequence instruction, which realizes above-mentioned method when being executed by processor.
The disclosure determines the client in each video content and merchandise items by carrying out structured analysis to each video content
Information, the weighting dimension for being then based on client and commodity determine emphasis commodity paid close attention to by client in each video content, finally
Interception includes the video clip for the emphasis commodity paid close attention to by client, and links to video clip, that is, is linked into complete video
All key contents for expressing client's focal point commodity, improve the effective information of video content, facilitate subsequent manager
It browsed, checked, compared and is analyzed.
By the detailed description referring to the drawings to the exemplary embodiment of the disclosure, the other feature of the disclosure and its
Advantage will become apparent.
Detailed description of the invention
The attached drawing for constituting part of specification describes embodiment of the disclosure, and together with the description for solving
Release the principle of the disclosure.
The disclosure can be more clearly understood according to following detailed description referring to attached drawing, in which:
Fig. 1 is the flow diagram of one embodiment of the method for disclosure association analysis Video Key content.
Fig. 2 is the flow diagram of another embodiment of the method for disclosure association analysis Video Key content.
Fig. 3 is the structural schematic diagram of one embodiment of the device of disclosure association analysis Video Key content.
Fig. 4 is the structural schematic diagram of another embodiment of the device of disclosure association analysis Video Key content.
Fig. 5 is the structural schematic diagram of one embodiment of the system of disclosure association analysis Video Key content.
Fig. 6 is an application schematic diagram of the method for disclosure association analysis Video Key content.
Fig. 7 is a realization configuration diagram of the system of disclosure association analysis Video Key content.
Fig. 8 is the structural schematic diagram of the further embodiment of the device of disclosure association analysis Video Key content.
Fig. 9 is the structural schematic diagram of another embodiment of the device of disclosure association analysis Video Key content.
Specific embodiment
The various exemplary embodiments of the disclosure are described in detail now with reference to attached drawing.It should also be noted that unless in addition having
Body explanation, the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
Scope of disclosure.
Simultaneously, it should be appreciated that for ease of description, the size of various pieces shown in attached drawing is not according to reality
Proportionate relationship draw.
Be to the description only actually of at least one exemplary embodiment below it is illustrative, never as to the disclosure
And its application or any restrictions used.
Technology, method and apparatus known to person of ordinary skill in the relevant may be not discussed in detail, but suitable
In the case of, the technology, method and apparatus should be considered as authorizing part of specification.
It is shown here and discuss all examples in, any occurrence should be construed as merely illustratively, without
It is as limitation.Therefore, the other examples of exemplary embodiment can have different values.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, then in subsequent attached drawing does not need that it is further discussed.
For the purposes, technical schemes and advantages of the disclosure are more clearly understood, below in conjunction with specific embodiment, and reference
The disclosure is further described in attached drawing.
Fig. 1 is the flow diagram of one embodiment of the method for disclosure association analysis Video Key content.
In step 110, multiple video contents are obtained.Wherein it is possible in the multiple cameras of monitoring point deployment, and obtain and respectively take the photograph
The content shot as head.Wherein, video content can be Online Video content and be also possible to video content.
In step 120, structured analysis is carried out to each video content, determines the client in each video content and merchandise items
Information.The people in video content, object are separated by structured analysis.
In step 130, the emphasis paid close attention to by client in each video content is determined based on the weighting dimension of client and commodity
Commodity.For example, pay close attention to direction by passenger flow Camera Positioning client stop place and client, according to client stop place with
The distance of commodity and client pay close attention to direction and the weighting dimension in commodity direction determines being closed in each video content by client
The emphasis commodity of note.
In step 140, interception includes the video clip for the emphasis commodity paid close attention to by client, and carries out chain to video clip
It connects.For example, first extracting the image information for the emphasis commodity paid close attention to by client, and key frame is marked, is then based on key frame interception
It include the video clip for the emphasis commodity paid close attention to by client in each video clip, and chronologically-based respectively to each video content
The video clip of middle client emphasis commodity of interest links, i.e., offer multichannel includes that the concentration of emphasis merchandise news regards
Frequently.
In this embodiment, by carrying out structured analysis to each video content, determine client in each video content and
Commodity object information, the weighting dimension for being then based on client and commodity determine the emphasis quotient paid close attention to by client in each video content
Product, finally interception includes the video clip for the emphasis commodity paid close attention to by client, and links to video clip, that is, has been linked into
All key contents of whole video expression client's focal point commodity, facilitate subsequent manager to browse, check, compare and divide
Analysis, solves the problems, such as that common monitoring video information amount is limited.
Fig. 2 is the flow diagram of another embodiment of the method for disclosure association analysis Video Key content.
In step 210, multiple video contents of associated playback are obtained.
In step 220, structured analysis is carried out to each video content, determines the client in each video content and merchandise items
Information.Wherein it is possible to carry out semantization processing to video file according to image preprocessing strategy, the people and quotient in video are isolated
Product, to be subsequently formed the descriptor format of the structuring to video data.
In step 230, direction is paid close attention to by passenger flow Camera Positioning client stop place and client.For example, passing through
The position of client can calculate client in the stop place in market in the installation site and video of video camera, and according to taking the photograph
The visual field direction of client determines the direction that client pays close attention in the installation direction of camera, shooting direction and video.In addition, also
It can determine that client pays close attention to the residence time information of certain commodity according to the residence time of client in video.
In step 240, weighting coefficient A and client pay close attention to side of the client stop place at a distance from commodity are obtained
To the weighting coefficient B with commodity direction.
In step 250, the weighting dimension of client and commodity is determined based on the distance parameter and directioin parameter of client and commodity,
Wherein, distance parameter is client stop place at a distance from commodity and the product of weighting coefficient A, directioin parameter are client's emphasis pass
Infuse the angle in direction and commodity direction and the product of weighting coefficient B.For example, client stop place is L, client at a distance from commodity
It is L*A+ α * B that the angle for paying close attention to direction and commodity direction, which is the weighting dimension of α, then client and commodity,.Furthermore it is also possible to examine
Client is considered to the residence time information T of certain commodity, if the weighting system of client's residence time is C, the weighting of client and commodity
Dimension is L*A+ α * B+T*C.Wherein, weighting coefficient can be configured according to the actual situation.
In step 260, if the weighting dimension of client and commodity is greater than weighting dimension threshold value, it is determined that commodity are video content
In by client pay close attention to emphasis commodity.For example, illustrating in video content if the weighting dimension of client and commodity is greater than 0.6
Commodity be the emphasis commodity paid close attention to by client, wherein weighting dimension threshold value can be set according to the actual situation.
By step 240-260, passenger flow can be associated with and show commodity.
In step 270, the image information for the emphasis commodity paid close attention to by client is extracted, and marks key frame.
In step 280, intercepted in each video clip based on key frame comprising the piece of video for the emphasis commodity paid close attention to by client
Section.
In step 290, the piece of video of chronologically-based emphasis commodity of interest to client in each video content respectively
Duan Jinhang link is linked as multichannel concentration video.
Furthermore it is also possible to by the video clip of the emphasis commodity of interest of client in each video content in same time point into
Row link, i.e. associated video content, are linked as the concentration video all the way comprising emphasis commodity in each video content.
In step 2100, the video clip of link being sent to client, being played with will pass through client concentration comprising quilt
The emphasis commodity video information of client's concern.Manager can watch the emphasis that certain period of time (moon, week) is paid close attention into customer family
The synthetic video of commodity is recorded a video.
Furthermore it is also possible to be marked in each video content based on client stop place and client's residence time with time point
Video is as index segment.For example, mark time+client stop place+residence time to be used as index title for the video clip,
Manager wants the video of examination by index pieces segment search.
In this embodiment, structured analysis video content is extracted, object in Combinatorial Optimization and associated video passes through counterweight
The extraction of point commodity video content is linked into the concentration video that can express all key contents that client pays close attention to commodity, solves
The limited problem of common monitoring video information amount, improves video monitoring key message amount, and providing for manager's optimization commodity can
By foundation.
Fig. 3 is the structural schematic diagram of one embodiment of the device of disclosure association analysis Video Key content.The device
Including video acquisition unit 310, structured analysis unit 320, emphasis commodity determination unit 330, video clip interception unit 340
With video clip link unit 350, in which:
Video acquisition unit 310 is for obtaining multiple video contents.Wherein it is possible in the multiple cameras of monitoring point deployment,
And obtain the content of each camera shooting.Wherein, video content can be Online Video content and be also possible to video content.
Structured analysis unit 320 is used to carry out structured analysis to each video content, determines the visitor in each video content
Family and commodity object information.The people in video content, object are separated by structured analysis.
Emphasis commodity determination unit 330 is used to determine based on the weighting dimension of client and commodity objective in each video content
The emphasis commodity of family concern.For example, direction is paid close attention to by passenger flow Camera Positioning client stop place and client, according to visitor
Family stop place is at a distance from commodity and client pays close attention to direction and the weighting dimension in commodity direction determines each video content
In by client pay close attention to emphasis commodity.
Video clip interception unit 340 is used to intercept the video clip of the emphasis commodity comprising being paid close attention to by client.For example, first
The image information for the emphasis commodity paid close attention to by client is extracted, and marks key frame, key frame is then based on and intercepts each video clip
In include the video clip of emphasis commodity paid close attention to by client.
Video clip link unit 350 is for linking video clip.For example, chronologically-based respectively to each view
The video clip of client's emphasis commodity of interest links in frequency content, i.e., offer multichannel includes the dense of emphasis merchandise news
Contracting video;Alternatively, the video clip of the emphasis commodity of interest of client in each video content in same time point is linked,
That is associated video content is linked as the concentration video all the way comprising emphasis commodity in each video content.
In this embodiment, by carrying out structured analysis to each video content, determine client in each video content and
Commodity object information, the weighting dimension for being then based on client and commodity determine the emphasis quotient paid close attention to by client in each video content
Product, finally interception includes the video clip for the emphasis commodity paid close attention to by client, and links to video clip, that is, has been linked into
All key contents of whole video expression client's focal point commodity, facilitate subsequent manager to browse, check, compare and divide
Analysis, solves the problems, such as that common monitoring video information amount is limited.
Fig. 4 is the structural schematic diagram of another embodiment of the device of disclosure association analysis Video Key content.The dress
It sets including video acquisition unit 410, structured analysis unit 420, customer information acquiring unit 430, emphasis commodity determination unit
440, video clip interception unit 450, video clip link unit 460 and video transmission unit 470, in which:
Video acquisition unit 410 is used to obtain multiple video contents of associated playback.
Structured analysis unit 420 is used to carry out structured analysis to each video content, determines the visitor in each video content
Family and commodity object information.
Customer information acquiring unit 430 is for passing through passenger flow Camera Positioning client stop place and the client side of paying close attention to
To.For example, the position of client can calculate client in the stop place in market in the installation site and video that pass through video camera
It sets, and determines that client pays close attention to according to the visual field direction of client in the installation direction of video camera, shooting direction and video
Direction.Furthermore it is also possible to determine that client pays close attention to the residence time information of certain commodity according to the residence time of client in video.
Emphasis commodity determination unit 440 is for obtaining weighting coefficient A, the Yi Jike of client stop place at a distance from commodity
The weighting coefficient B in direction Yu commodity direction is paid close attention at family, determines visitor based on the distance parameter and directioin parameter of client and commodity
The weighting dimension at family and commodity, wherein distance parameter be client stop place at a distance from commodity with the product of weighting coefficient A,
Directioin parameter is that client pays close attention to the angle in direction and commodity direction and the product of weighting coefficient B, if client and commodity plus
It weighs dimension and is greater than weighting dimension threshold value, it is determined that commodity are the emphasis commodity paid close attention to by client in video content.For example, client
Stop place is L at a distance from commodity, and it is adding for α, then client and commodity that client, which pays close attention to direction and the angle in commodity direction,
Power dimension is L*A+ α * B.Additionally, it is also contemplated that residence time information T of the client to certain commodity, if client's residence time adds
Power system is C, then the weighting dimension of client and commodity is L*A+ α * B+T*C.Wherein, weighting coefficient can according to the actual situation into
Row setting.
Video clip interception unit 450 is used to extract the image information for the emphasis commodity paid close attention to by client, and marks key
Frame is intercepted in each video clip based on key frame comprising the video clip for the emphasis commodity paid close attention to by client.
Video clip link unit 460 is for the chronologically-based emphasis of interest to client in each video content respectively
The video clip of commodity carries out link or by the view of the emphasis commodity of interest of client in each video content in same time point
Frequency segment is linked.
Video transmission unit 470 is used to the video clip of link being sent to client, is broadcast with will pass through client concentration
Put the emphasis commodity video information comprising being paid close attention to by client.Manager wants the video of examination by index pieces segment search, such as
The synthetic video video recording for the emphasis commodity that viewing certain period of time (moon, week) is paid close attention into customer family.
In addition, the device can also include index segment determination unit, for resident based on client stop place and client
Time marks in each video content with the video at time point as index segment.For example, marking time+visitor for the video clip
Family stop place+residence time wants the video of examination by index pieces segment search as index title, manager.
In this embodiment, structured analysis video content is extracted, object in Combinatorial Optimization and associated video passes through counterweight
The extraction of point commodity video content is linked into the concentration video that can express all key contents that client pays close attention to commodity, solves
The limited problem of common monitoring video information amount, improves video monitoring key message amount, and providing for manager's optimization commodity can
By foundation.
Fig. 5 is the structural schematic diagram of one embodiment of the system of disclosure association analysis Video Key content.The system
Including commodity video camera 510, passenger flow video camera 520, client 530 and association analysis Video Key content device 540,
In, the device 540 of association analysis Video Key content is described in detail in the above-described embodiments, herein not further
It illustrates.Commodity video camera 510 is for example arranged near each sales counter in market, for shooting the condition of merchandise of each sales counter, the commodity
Video camera can photograph the nigh activity of client simultaneously, for example, the behaviors such as client's browsing, purchase commodity.Passenger flow video camera 520
Such as it can be in acquisition passenger flow information such as mall entrance etc..Client 530 can receive association analysis Video Key content
The concentration video information that device 540 is sent includes the concentration video of emphasis merchandise news, in order to which manager's progress is subsequent clear
It lookes at, check, compare and analyzes, for example, better marketing tool etc. can be set by video.
In a particular application, as shown in fig. 6, in step 610, client can be used to check that hot spot commodity regard for administrative staff
Frequently.
In step 620, the device of association analysis Video Key content is sent to passenger flow video camera obtains asking for passenger flow video
It asks, passenger flow video camera returns to passenger flow video.One group of video camera is called to carry out video association analysis.
Passenger flow analysing is carried out in the device inquiry passenger flow video of step 630, association analysis Video Key content, obtains passenger flow
The information such as time point and position are paid close attention to, and carry out video matching, the video informations such as positioning concern commodity.For example, visitor can be passed through
Stream concern time point and position etc. can determine the emphasis commodity of user's concern.
In step 640, the device of association analysis Video Key content is to client restoring to normal position information.
It is sent in the camera for the emphasis commodity that step 650, client are paid close attention to shooting user and obtains hot video information
Request.
In step 660, commodity video camera returns to video flowing to client.User checks that hot spot commodity regard by the client
Frequently.
In the above-described embodiments, hot spot commodity video is played by concentration and is supplied to manager's hot spot commodity synthetic video letter
Breath, solves the problems, such as that common monitoring video information amount is limited, improves video monitoring key message amount, optimizes commodity for manager and mentions
Reliable basis is supplied.
It will be understood by those of skill in the art that the function that each unit of above system can be realized can be set with one
It is standby to realize, it can use two or more independent equipment also to realize, for example, Fig. 7 is that disclosure system realizes framework
One schematic diagram.Video monitoring platform obtains video information, and intellectual analysis manages unit and carries out the operation such as video analysis, association,
Center can be calculated in specific implementation by data and carries out data calculating, analysis result temporary storage location is for keeping in video analysis knot
Fruit, media storage association platform is for storing video association analysis as a result, may search for going for by video search abstract
Information, using show system can provide multi-channel video concentration result.
Fig. 8 is the structural schematic diagram of the further embodiment of the device of disclosure association analysis Video Key content.The dress
It sets including memory 810 and processor 820.Wherein: memory 810 can be disk, flash memory or other any non-volatile deposit
Storage media.Memory 810 is used to store the instruction in embodiment corresponding to Fig. 1-2.Processor 820 is coupled to memory 810, can
To implement as one or more integrated circuits, such as microprocessor or microcontroller.The processor 820 is for executing storage
The instruction stored in device.
It in one embodiment, can be as shown in figure 9, the device 900 includes memory 910 and processor 920.Processing
Device 920 is coupled to memory 910 by BUS bus 930.The device 900 can also be connected to outside by memory interface 940 and deposit
Storage device 950 can also be connected to network or an other department of computer science to call external data by network interface 960
System (not shown), no longer describes in detail herein.
In this embodiment, it is instructed by memory stores data, then above-metioned instruction is handled by processor, solved general
The limited problem of logical monitoring video information amount.
In another embodiment, a kind of computer readable storage medium, is stored thereon with computer program instructions, this refers to
The step of order realizes the method in embodiment corresponding to Fig. 1-2 when being executed by processor.It should be understood by those skilled in the art that,
Embodiment of the disclosure can provide as method, apparatus or computer program product.Therefore, complete hardware reality can be used in the disclosure
Apply the form of example, complete software embodiment or embodiment combining software and hardware aspects.Moreover, the disclosure can be used one
It is a or it is multiple wherein include computer usable program code computer can with non-transient storage medium (including but not limited to
Magnetic disk storage, CD-ROM, optical memory etc.) on the form of computer program product implemented.
The disclosure is reference according to the method for the embodiment of the present disclosure, the flow chart of equipment (system) and computer program product
And/or block diagram describes.It should be understood that each process in flowchart and/or the block diagram can be realized by computer program instructions
And/or the combination of the process and/or box in box and flowchart and/or the block diagram.It can provide these computer programs to refer to
Enable the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to generate
One machine so that by the instruction that the processor of computer or other programmable data processing devices executes generate for realizing
The device for the function of being specified in one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
So far, the disclosure is described in detail.In order to avoid covering the design of the disclosure, it is public that this field institute is not described
The some details known.Those skilled in the art as described above, completely it can be appreciated how implementing technology disclosed herein
Scheme.
Although being described in detail by some specific embodiments of the example to the disclosure, the skill of this field
Art personnel it should be understood that above example merely to be illustrated, rather than in order to limit the scope of the present disclosure.The skill of this field
Art personnel are it should be understood that can modify to above embodiments in the case where not departing from the scope of the present disclosure and spirit.This public affairs
The range opened is defined by the following claims.
Claims (15)
1. a kind of method of association analysis Video Key content, comprising:
Obtain multiple video contents;
Structured analysis is carried out to each video content, determines the client in each video content and commodity object information;
The emphasis commodity paid close attention to by client in each video content are determined based on the weighting dimension of client and commodity;
Interception includes the video clip for the emphasis commodity paid close attention to by client, and links to the video clip.
2. according to the method described in claim 1, further include:
Direction is paid close attention to by passenger flow Camera Positioning client stop place and client;
Based on client stop place at a distance from commodity and client pays close attention to the weighting dimension in direction and commodity direction and determines
The emphasis commodity paid close attention to by client in each video content.
3. according to the method described in claim 2, wherein,
It obtains weighting coefficient A and client of the client stop place at a distance from commodity and pays close attention to direction and commodity direction
Weighting coefficient B;
The weighting dimension of the client and commodity is determined based on the distance parameter and directioin parameter of client and commodity, wherein described
Distance parameter is client stop place at a distance from commodity and the product of weighting coefficient A, the directioin parameter are client's emphasis pass
Infuse the angle in direction and commodity direction and the product of weighting coefficient B;
If the weighting dimension of the client and commodity is greater than weighting dimension threshold value, it is determined that the commodity are the quilt in video content
The emphasis commodity of client's concern.
4. according to the method described in claim 2, further include:
Client's residence time information is obtained by passenger flow video camera;
The video in each video content with time point is marked as rope based on client stop place and client's residence time
Leader section.
5. method according to claim 1 to 4, wherein
The image information for the emphasis commodity paid close attention to by client is extracted, and marks key frame;
It is intercepted in each video clip based on key frame comprising the video clip for the emphasis commodity paid close attention to by client;
The video clip of chronologically-based emphasis commodity of interest to client in each video content respectively links;
Or
The video clip of the emphasis commodity of interest of client in each video content in same time point is linked.
6. according to the method described in claim 5, further include:
The video clip of link is sent to client, plays the weight comprising being paid close attention to by client will pass through the client concentration
Point commodity video information.
7. a kind of device of association analysis Video Key content, comprising:
Video acquisition unit, for obtaining multiple video contents;
Structured analysis unit determines the client in each video content for carrying out structured analysis to each video content
And commodity object information;
Emphasis commodity determination unit, for based on the weighting dimension of client and commodity determine in each video content by client
The emphasis commodity of concern;
Video clip interception unit, for intercepting the video clip of the emphasis commodity comprising being paid close attention to by client;
Video clip link unit, for being linked to the video clip.
8. device according to claim 7, further includes:
Customer information acquiring unit, for passing through passenger flow Camera Positioning client stop place and stop directional information;
The emphasis commodity determination unit is used for based on client stop place at a distance from commodity and client pays close attention to direction
The emphasis commodity paid close attention to by client in each video content are determined with the weighting dimension in commodity direction.
9. device according to claim 8, wherein
The emphasis commodity determination unit is also used to obtain weighting coefficient A, the Yi Jike of client stop place at a distance from commodity
Pay close attention to the weighting coefficient B in direction Yu commodity direction in family;Institute is determined based on the distance parameter and directioin parameter of client and commodity
State the weighting dimension of client and commodity, wherein the distance parameter be client stop place at a distance from commodity with weighting coefficient A
Product, the directioin parameter is that client pays close attention to the angle in direction and commodity direction and the product of weighting coefficient B;If described
The weighting dimension of client and commodity is greater than weighting dimension threshold value, it is determined that the commodity are being paid close attention in video content by client
Emphasis commodity.
10. device according to claim 8, further includes:
Segment determination unit is indexed, for marking in each video content based on client stop place and client's residence time
Video with time point is as index segment;
Wherein, the customer information acquiring unit is also used to obtain client's residence time information by passenger flow video camera.
11. according to any device of claim 7-10, wherein
The video clip interception unit is used to extract the image information for the emphasis commodity paid close attention to by client, and marks key frame,
It is intercepted in each video clip based on key frame comprising the video clip for the emphasis commodity paid close attention to by client;
The video clip link unit is for the chronologically-based weight of interest to client in each video content respectively
The video clip of point commodity is linked, or the emphasis commodity that client in each video content in same time point is of interest
Video clip linked.
12. device according to claim 11, further includes:
Video transmission unit is played for the video clip of link to be sent to client with will pass through the client concentration
Include the emphasis commodity video information paid close attention to by client.
13. a kind of system of association analysis Video Key content, including commodity video camera, passenger flow video camera, client and right
It is required that the device of any association analysis Video Key content of 7-12.
14. a kind of device of association analysis Video Key content, comprising:
Memory;And
It is coupled to the processor of the memory, the processor is configured to based on the instruction execution for being stored in the memory
Such as method as claimed in any one of claims 1 to 6.
15. a kind of computer readable storage medium, is stored thereon with computer program instructions, real when which is executed by processor
The step of existing method as claimed in any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711219871.2A CN109842817B (en) | 2017-11-29 | 2017-11-29 | Method, device and system for analyzing video key content in association manner |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711219871.2A CN109842817B (en) | 2017-11-29 | 2017-11-29 | Method, device and system for analyzing video key content in association manner |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109842817A true CN109842817A (en) | 2019-06-04 |
CN109842817B CN109842817B (en) | 2022-02-08 |
Family
ID=66881456
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711219871.2A Active CN109842817B (en) | 2017-11-29 | 2017-11-29 | Method, device and system for analyzing video key content in association manner |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109842817B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010039518A1 (en) * | 2000-04-07 | 2001-11-08 | Hiroshi Ishizuka | Commodity retrieval method |
EP1213675A2 (en) * | 2000-12-07 | 2002-06-12 | Sony Corporation | Information providing method and system and information providing apparatus |
JP2004234646A (en) * | 2003-01-06 | 2004-08-19 | Hiroshi Sato | Content relevant information providing device, content relevant information providing method, content relevant information providing system, portable terminal and information processing system |
WO2009146139A2 (en) * | 2008-04-03 | 2009-12-03 | Fort Boise Produce Company | Methods and systems for accessing information related to an order of a commodity |
CN101639921A (en) * | 2009-08-21 | 2010-02-03 | 于学先 | Network data exchange method and network server |
CN102122346A (en) * | 2011-02-28 | 2011-07-13 | 济南纳维信息技术有限公司 | Video analysis-based physical storefront customer interest point acquisition method |
JP2015001879A (en) * | 2013-06-17 | 2015-01-05 | キヤノン株式会社 | Information processing apparatus, information processing system, and program |
CN104902345A (en) * | 2015-05-26 | 2015-09-09 | 多维新创(北京)技术有限公司 | Method and system for realizing interactive advertising and marketing of products |
CN105916048A (en) * | 2015-12-25 | 2016-08-31 | 乐视致新电子科技(天津)有限公司 | Method, server and client for associating program video with article |
CN106202282A (en) * | 2016-07-01 | 2016-12-07 | 刘青山 | Multi-media network shopping guidance system |
CN106792006A (en) * | 2017-01-17 | 2017-05-31 | 南通同洲电子有限责任公司 | Commodity supplying system and method based on video |
-
2017
- 2017-11-29 CN CN201711219871.2A patent/CN109842817B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010039518A1 (en) * | 2000-04-07 | 2001-11-08 | Hiroshi Ishizuka | Commodity retrieval method |
EP1213675A2 (en) * | 2000-12-07 | 2002-06-12 | Sony Corporation | Information providing method and system and information providing apparatus |
JP2004234646A (en) * | 2003-01-06 | 2004-08-19 | Hiroshi Sato | Content relevant information providing device, content relevant information providing method, content relevant information providing system, portable terminal and information processing system |
WO2009146139A2 (en) * | 2008-04-03 | 2009-12-03 | Fort Boise Produce Company | Methods and systems for accessing information related to an order of a commodity |
CN101639921A (en) * | 2009-08-21 | 2010-02-03 | 于学先 | Network data exchange method and network server |
CN102122346A (en) * | 2011-02-28 | 2011-07-13 | 济南纳维信息技术有限公司 | Video analysis-based physical storefront customer interest point acquisition method |
JP2015001879A (en) * | 2013-06-17 | 2015-01-05 | キヤノン株式会社 | Information processing apparatus, information processing system, and program |
CN104902345A (en) * | 2015-05-26 | 2015-09-09 | 多维新创(北京)技术有限公司 | Method and system for realizing interactive advertising and marketing of products |
CN105916048A (en) * | 2015-12-25 | 2016-08-31 | 乐视致新电子科技(天津)有限公司 | Method, server and client for associating program video with article |
CN106202282A (en) * | 2016-07-01 | 2016-12-07 | 刘青山 | Multi-media network shopping guidance system |
CN106792006A (en) * | 2017-01-17 | 2017-05-31 | 南通同洲电子有限责任公司 | Commodity supplying system and method based on video |
Non-Patent Citations (1)
Title |
---|
陈中华,张潭,王林光: ""基于视频内容挖掘的顾客行为感知分析研究"", 《信息与电脑》 * |
Also Published As
Publication number | Publication date |
---|---|
CN109842817B (en) | 2022-02-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104919794B (en) | For extracting the method and system of metadata from master-slave mode camera tracking system | |
US11756367B2 (en) | Investigation generation in an observation and surveillance system | |
CN108509941B (en) | Emotion information generation method and device | |
US10970334B2 (en) | Navigating video scenes using cognitive insights | |
CN103548025B (en) | The method and termination of the object included in supporting collection input picture | |
Korshunov et al. | PEViD: privacy evaluation video dataset | |
Cioppa et al. | Scaling up SoccerNet with multi-view spatial localization and re-identification | |
Srivastav et al. | Human pose estimation on privacy-preserving low-resolution depth images | |
US8917909B2 (en) | Surveillance including a modified video data stream | |
KR101821982B1 (en) | Evaluation of augmented reality skins | |
CN109766736A (en) | Face identification method, device and system | |
Yadav et al. | An improved deep learning-based optimal object detection system from images | |
Li et al. | CVPE: A computer vision approach for scalable and privacy-preserving socio-spatial, multimodal learning analytics | |
US9767564B2 (en) | Monitoring of object impressions and viewing patterns | |
CN110246280B (en) | Human-cargo binding method and device, computer equipment and readable medium | |
CN109842817A (en) | The methods, devices and systems of association analysis Video Key content | |
Núñez et al. | Computational collective intelligence | |
WO2022188599A1 (en) | Selective redaction of images | |
Grosselfinger et al. | An architecture for automatic multimodal video data anonymization to ensure data protection | |
Stefański et al. | The problem of detecting boxers in the boxing ring | |
Firoze et al. | Scoring photographic rule of thirds in a large MIRFLICKR dataset: A showdown between machine perception and human perception of image aesthetics | |
Vaiyapuri et al. | A convolutional neural network for face mask detection in IoT-based smart healthcare systems | |
WO2023238614A1 (en) | Information processing device, information processing system, information processing method, and program | |
Dahmane et al. | Are you smiling as a celebrity? latent smile and gender recognition | |
Neumann et al. | Interaction analysis and joint attention tracking in augmented reality |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |