CN109522449A - Searching method and device - Google Patents
Searching method and device Download PDFInfo
- Publication number
- CN109522449A CN109522449A CN201811136192.3A CN201811136192A CN109522449A CN 109522449 A CN109522449 A CN 109522449A CN 201811136192 A CN201811136192 A CN 201811136192A CN 109522449 A CN109522449 A CN 109522449A
- Authority
- CN
- China
- Prior art keywords
- effective
- terminal
- result
- frame
- server
- 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
Abstract
The present invention provides a kind of searching method and device.This method comprises: at least two effective video frames that server receiving terminal is sent, the at least two effective videos frame is that the terminal is extracted from the video flowing got, and the corresponding shooting angle of each effective video frame is different in at least two effective videos frame;The server identifies at least two effective videos frame, obtains at least two recognition results, and at least two effective videos frame and at least two recognition result correspond;The server obtains target identification result according at least two recognition result;The server is according to the target identification as a result, obtaining search result;Described search result is sent to the terminal by the server.Improve recognition accuracy.
Description
Technical field
The present invention relates to search technique field more particularly to a kind of searching methods and device.
Background technique
Web search refers to the process of that user is scanned for using information of the search engine to desired acquisition.Web search tool
The features such as having strong real-time, convenient degree high and humongous search results can be obtained, the most used interconnection of user is become
One of net function.When user carries out internet hunt, the way of search being commonly used has: typewriting input and voice input.However,
Both input modes are that user knows what the case where search key is.When user is not aware that search key is assorted
When, such as: user wants to obtain the relevant information of a certain plant seen, but when not knowing the title of this plant, it uses
Family cannot realize search process by above-mentioned way of search.
In the prior art, it can shoot to obtain the picture of article to be searched by terminal, then the picture is identified, into
And scanned for according to recognition result, obtain the relevant information of article to be searched.But the angle of above-mentioned shooting picture is fixed
, the recognition result accuracy obtained according to the picture is not high.
Summary of the invention
The present invention provides a kind of searching method and device, for improving the accuracy of recognition result.
In a first aspect, the present invention provides a kind of searching method, comprising:
At least two effective video frames that server receiving terminal is sent, at least two effective videos frame is the end
End is extracted from the video flowing got, the corresponding shooting angle of each effective video frame in at least two effective videos frame
Degree is different;
The server identifies at least two effective videos frame, obtains at least two recognition results, described
At least two effective video frames and at least two recognition result correspond;
The server obtains target identification result according at least two recognition result;
The server is according to the target identification as a result, obtaining search result;
Described search result is sent to the terminal by the server.
Optionally, at least two recognition result is corresponding at least two text of at least two effective videos frame
Description.
Optionally, the server obtains target identification result according at least two recognition result, comprising:
The server regard the maximum text description of accounting at least two text description as the target identification
As a result.
Optionally, the server is according to the target identification as a result, obtaining search result, comprising:
The server searches the search result to match with the target identification result in the database.
Second aspect, the present invention provide a kind of searching method, comprising:
Terminal obtains video flowing;
The terminal extracts at least two effective video frames from the video flowing, in at least two effective videos frame
The corresponding shooting angle of each effective video frame is different;
At least two effective videos frame is sent to server by the terminal, and at least two effective videos frame is used
In indicating that the server identifies at least two effective videos frame, at least two recognition results are obtained, and according to
At least two recognition result, obtains target identification result;And then according to the target identification as a result, obtaining search result;
The terminal receives and shows the described search result that the server is sent.
Optionally, the terminal obtains video flowing, comprising:
The terminal shoots to obtain the video flowing by the camera of the terminal.
Optionally, the terminal obtains video flowing, comprising:
The terminal receives user from the video flowing locally uploaded.
Optionally, the terminal extracts at least two effective video frames from the video flowing, comprising:
The terminal obtains the corresponding gyro data of each video frame in the video flowing;
The terminal determines at least two effective video according to the corresponding gyro data of each video frame
Frame.
Optionally, the gyro data includes angle value, two neighboring effective in at least two effective videos frame
The difference of the corresponding angle value of video frame is greater than preset value.
The third aspect, the present invention provide a kind of searcher, comprising:
Receiving module, for receiving at least two effective video frames of terminal transmission, at least two effective videos frame
It is that the terminal is extracted from the video flowing got, each effective video frame is corresponding in at least two effective videos frame
Shooting angle it is different;
Identification module obtains at least two recognition results, institute for identifying at least two effective videos frame
It states at least two effective video frames and at least two recognition result corresponds;
Processing module, for obtaining target identification result according at least two recognition result;
Module is obtained, is used for according to the target identification as a result, obtaining search result;
Sending module, for described search result to be sent to the terminal.
Optionally, at least two recognition result is corresponding at least two text of at least two effective videos frame
Description.
Optionally, the processing module, specifically for retouching the maximum text of accounting at least two text description
It states as the target identification result.
Optionally, the acquisition module matches specifically for searching in the database with the target identification result
Search result.
Fourth aspect, the present invention provide a kind of searcher, comprising:
Module is obtained, for obtaining video flowing;
Extraction module, for extracting at least two effective video frames from the video flowing, described at least two are effectively regarded
The corresponding shooting angle of each effective video frame is different in frequency frame;
Sending module, for at least two effective videos frame to be sent to server, described at least two are effectively regarded
Frequency frame is used to indicate the server and identifies at least two effective videos frame, obtains at least two recognition results,
And according at least two recognition result, target identification result is obtained;And then according to the target identification as a result, obtaining search
As a result;
Receiving module, the described search result sent for receiving and showing the server.
Optionally, the acquisition module shoots to obtain the video flowing specifically for the camera by the terminal.
Optionally, the acquisition module, specifically for receiving user from the video flowing locally uploaded.
Optionally, the extraction module, specifically for the corresponding gyroscope number of video frame each in the acquisition video flowing
According to;According to the corresponding gyro data of each video frame, at least two effective videos frame is determined.
Optionally, the gyro data includes angle value, two neighboring effective in at least two effective videos frame
The difference of the corresponding angle value of video frame is greater than preset value.
5th aspect, the present invention provide a kind of computer readable storage medium, are stored thereon with computer program, the meter
The step of calculation machine program realizes server side in above-mentioned searching method when being executed by processor.
6th aspect, the present invention provide a kind of computer readable storage medium, are stored thereon with computer program, the meter
The step of calculation machine program realizes terminal side in above-mentioned searching method when being executed by processor.
7th aspect, the present invention provide a kind of server, comprising:
Processor;And
Memory, for storing the executable instruction of the processor;
Wherein, the processor is configured to realize server in above-mentioned searching method via the executable instruction is executed
The step of side.
Eighth aspect, the present invention provide a kind of terminal, comprising:
Processor;And
Memory, for storing the executable instruction of the processor;
Wherein, the processor is configured to realize terminal side in above-mentioned searching method via the executable instruction is executed
The step of.
Searching method and device provided in this embodiment after terminal gets video flowing, extract at least two from video flowing
A effective video frame is simultaneously sent to server, and server is identified to obtain at least two knowledges at least two effective videos frame
Not as a result, and obtaining target identification according at least two recognition results as a result, improving recognition accuracy.
Detailed description of the invention
Fig. 1 is system schematic provided by the invention;
Fig. 2 is the signaling process figure of the embodiment one of searching method provided by the invention;
Fig. 3 is the schematic diagram provided by the invention for knowing figure webpage;
Fig. 4 is the schematic diagram provided by the invention for obtaining target identification result;
Fig. 5 is the signaling process figure of the embodiment two of searching method provided by the invention;
Fig. 6 is another schematic diagram provided by the invention for obtaining target identification result;
Fig. 7 is user interface schematic diagram provided by the invention;
Fig. 8 is the structural schematic diagram of the embodiment one of searcher provided by the invention;
Fig. 9 is the structural schematic diagram of the embodiment two of searcher provided by the invention;
Figure 10 is the hardware structural diagram of server provided by the invention;
Figure 11 is the hardware structural diagram of terminal provided by the 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.
In order to obtain the relevant information of certain article, in the prior art, user can shoot to obtain the figure of the article by terminal
Then piece identifies the picture, and then searched for obtain the relevant information of the article according to recognition result.However, due to clapping
Angle is fixed when taking the photograph picture, therefore the information for shooting the article for including in obtained picture has limitation, according only to the picture
Obtained recognition result accuracy is not high.
Based on above-mentioned technical problem, the present invention provides a kind of searching method and device, user and can shoot to obtain by terminal
The video flowing of article, terminal can extract the picture obtained for multiple shooting angle of the article and be sent to from the video flowing
Server, server can identify the picture of multiple shooting angle to obtain multiple recognition results, then according to multiple knowledges
Other result obtains target identification as a result, searching for obtain the related content of article according to the target identification result in turn.Due to multiple
The information for the article that the picture of shooting angle includes be it is abundant, obtained according to the recognition result of the picture of multiple shooting angle
Target identification result precision is higher.
Fig. 1 is the system schematic provided by the invention that can be used for implementing above-mentioned searching method.System shown in Figure 1 includes:
Terminal and server.
Wherein, terminal is the terminal with shooting video capability, is connected between terminal and server by wireless technology, eventually
It holds for article progress video capture to be searched, obtaining the video flowing of article to be searched, and extracting from the video flowing to have
Video frame is imitated, and then effective video frame is sent to server.Server is used to receive the effective video frame of user's transmission, and right
The effective video frame is identified, obtains multiple recognition results, and then obtain target identification result according to multiple recognition results;Most
It searches for obtain the search result of article to be searched according to target identification result afterwards and returns to terminal.
Optionally, terminal can be desktop computer, notebook, personal digital assistant (Personal Digital
Assistant, referred to as: PDA), smart phone and plate apparatus such as computer, terminal is illustrated with smart phone in Fig. 1.
How to be solved with technical solution of the specifically embodiment to technical solution of the present invention and the application below above-mentioned
Technical problem is described in detail.These specific embodiments can be combined with each other below, for the same or similar concept
Or process may repeat no more in certain embodiments.Below in conjunction with attached drawing, the embodiment of the present invention is described.
Fig. 2 is the signaling process figure of the embodiment one of searching method provided by the invention.As shown in Fig. 2, the present embodiment mentions
The searching method of confession, comprising:
S201, terminal obtain video flowing.
Wherein, terminal obtains a kind of implementation of the video flowing of article to be searched are as follows: the terminal passes through the terminal
Camera shoot to obtain the video flowing.
Detailed process is that the mark of knowledge figure webpage can be arranged on a web browser, and user wants to obtain the phase of article to be searched
Close information when, first open a terminal on browser, then by above-mentioned knowledge figure webpage mark triggering open specify knowledge figure net
Page, it is shown in Figure 3, know settable graphics display area (region that dotted line frame is included in Fig. 3), shooting time on figure webpage
Display area and start recognition button, terminal camera first can be directed at article to be searched by user, then click start identification by
Button, browser will obtain the content that camera is being shot using webRTC agreement, in the above-mentioned shooting to article to be searched
Period, terminal can real-time prompting user adjust shooting angle so that obtained view of the video stream packets containing multiple and different angles of shooting
Frequency frame.When the duration that shooting time display area is shown reaches preset duration, terminal is automatically stopped shooting.User can stop
After shooting, the video flowing that shooting obtains is submitted manually, side can also be shot by terminal edge and submitted.
Terminal obtains another implementation of the video flowing of article to be searched are as follows: the terminal receives user from this ground
The video flowing passed.
Detailed process is, when user wants to obtain the relevant information of article to be searched, can will be shot by terminal camera
The video flowing of obtained article to be searched is stored in local, then opens browser, is opened by browser and uploads the page, passed through
The upload page uploads the video flowing of preservation.
S202, terminal extract at least two effective video frames from the video flowing.
Wherein, the corresponding shooting angle of each effective video frame is different in at least two effective videos frame.
At least two effective videos frame is sent to server by S203, terminal.
S204, server identify at least two effective videos frame, obtain at least two recognition results, described
At least two effective video frames and at least two recognition result correspond.
S205, server obtain target identification result according at least two recognition result.
For example, it participates in shown in Fig. 4, it is assumed that at least two effective video frames that server receives are respectively as follows: effectively
Video frame 1, effective video frame 2 ..., effective video frame N.N number of effective video frame is identified, obtained recognition result
Be respectively as follows: recognition result 1, recognition result 2 ..., recognition result N;It is for statistical analysis to N number of recognition result to obtain
Target identification result.
S206, server are according to the target identification as a result, obtaining search result.
Described search result is sent to terminal by S207, server.
S208, terminal show described search result.
Due to target identification the result is that the recognition result of the video frame based on multiple and different shooting angle obtained, it is multiple not
The information for the article to be searched that video frame with shooting angle includes is more comprehensive, therefore compared to the prior art, target identification knot
The accuracy of fruit is higher, correspondingly, being the search result and article to be searched obtained according to search with the target identification result
Matching degree also correspondinglys increase.
Searching method provided in this embodiment after terminal gets video flowing, extracts at least two effectively from video flowing
Video frame is simultaneously sent to server, and server is identified to obtain at least two identification knots at least two effective videos frame
Fruit, and target identification is obtained as a result, improving recognition accuracy according at least two recognition results.
The tool of at least two effective video frames is extracted from the video flowing below for terminal in above-described embodiment S202
Server is identified to obtain target identification at least two effective videos frame in body implementation process and S204-S205
As a result specific implementation process is described in detail.
Fig. 5 is the signaling process figure of the embodiment two of searching method provided by the invention, as shown in figure 5, the present embodiment mentions
The searching method of confession, comprising:
S501, terminal obtain video flowing.
This step specific implementation can be found in the S201 in above-described embodiment, and details are not described herein.
S502, terminal obtain the corresponding gyro data of each video frame in the video flowing.
S503, the terminal determine described at least two effectively according to the corresponding gyro data of each video frame
Video frame.
Specifically, since video frame each in video flowing has a corresponding gyro data, the gyro data packet
Angle information when shooting video is included, i.e., each video frame corresponds to an angle value, can be by the first frame image of video flowing
As first effective video frame, and using the angle value of first frame image as foundation, successively judge to connect down according to video flowing timing
The difference of the angle value of the video frame and the first frame image come, difference is greater than the video frame of preset value if it exists, then by the video
Frame is as second effective video frame, similarly, using the angle value of second video frame as foundation, obtain third video frame,
4th video frame ..., n-th video frame.
At least two effective videos frame is sent to server by S504, terminal.
S505, server identify at least two effective videos frame, obtain the description of at least two texts.
Wherein, at least two effective video frames and at least two text description correspond.
S506, server regard the maximum text description of accounting at least two text description as the target identification
As a result.
Citing comes institute, and user shoots to obtain a kind of video flowing of plant by terminal, available by above-mentioned S501-S503
Effective video frame of the plant under different shooting angles, is respectively as follows: effective video frame 1, effective video frame 2, effective video frame
3, effective video frame 4 and effective video frame 5, it is shown in Figure 6.Assuming that the recognition result of effective video frame 1 are as follows: dendrobium nobile;It is right
Effective video frame 2, effective video frame 3, the recognition result of effective video frame 4 and effective video frame 5 are equal are as follows: orchid.Due to orchid
Accounting is maximum in recognition result, therefore can be using orchid as target identification result.
As it can be seen that target identification is the result is that the recognition result based on the video frame to multiple and different shooting angle obtained, no
The information for the article that video frame with shooting angle includes is more comprehensive, improves the accuracy of target identification result.
S507, server are according to the target identification as a result, obtaining search result.
Described search result is sent to terminal by S508, server.
S509, terminal show described search result.
Optionally, search result can be encyclopaedia data, as shown in Figure 7.
Searching method provided in this embodiment describes the implementation that terminal extracts effective video frame from video flowing,
And server identifies effective video frame, obtains the implementation of target identification result, provides through this embodiment
The recognition accuracy to article to be searched can be improved in implementation.
Fig. 8 is the structural schematic diagram of the embodiment one of searcher provided by the invention.As shown in figure 8, the present embodiment mentions
The searcher of confession, comprising:
Receiving module 801, for receiving at least two effective video frames of terminal transmission, at least two effective video
Frame is that the terminal is extracted from the video flowing got, each effective video frame pair in at least two effective videos frame
The shooting angle answered is different;
Identification module 802 obtains at least two identification knots for identifying at least two effective videos frame
Fruit, at least two effective videos frame and at least two recognition result correspond;
Processing module 803, for obtaining target identification result according at least two recognition result;
Module 804 is obtained, is used for according to the target identification as a result, obtaining search result;
Sending module 805, for described search result to be sent to the terminal.
Optionally, at least two recognition result is corresponding at least two text of at least two effective videos frame
Description.
Optionally, the processing module 803 is specifically used for the maximum text of accounting at least two text description
Description is used as the target identification result.
Optionally, the acquisition module 804, matches specifically for searching in the database with the target identification result
Search result.
Searcher provided in this embodiment can be used for the step of executing server side in above method embodiment, in fact
Existing principle is similar with technical effect, and details are not described herein.
Fig. 9 is the structural schematic diagram of the embodiment two of searcher provided by the invention.As shown in figure 9, the present embodiment mentions
The searcher of confession, comprising:
Module 901 is obtained, obtains video flowing for terminal;
Extraction module 902, for extracting at least two effective video frames from the video flowing, described at least two effectively
The corresponding shooting angle of each effective video frame is different in video frame;
Sending module 903, for at least two effective videos frame to be sent to server, described at least two effectively
Video frame is used to indicate the server and identifies at least two effective videos frame, obtains at least two identification knots
Fruit, and according at least two recognition result, obtain target identification result;And then according to the target identification as a result, obtaining
Search result;
Receiving module 904, the described search result sent for receiving and showing the server.
Optionally, the acquisition module 901, shoots to obtain the video specifically for the camera by the terminal
Stream.
Optionally, the acquisition module 901, specifically for receiving user from the video flowing locally uploaded.
Optionally, the extraction module 902, specifically for the corresponding gyroscope of video frame each in the acquisition video flowing
Data;According to the corresponding gyro data of each video frame, at least two effective videos frame is determined.
Optionally, the gyro data includes angle value, two neighboring effective in at least two effective videos frame
The difference of the corresponding angle value of video frame is greater than preset value.
Searcher provided in this embodiment can be used for the step of executing terminal side in above method embodiment, realize
Principle is similar with technical effect, and details are not described herein.
Figure 10 is the hardware structural diagram of server provided by the invention.As shown in Figure 10, the server of the present embodiment
May include:
Memory 1001, for storing program instruction.
Processor 1002 realizes server side in any of the above-described embodiment of the method for being performed in described program instruction
The step of, specific implementation principle can be found in above-described embodiment.
Figure 11 is the hardware structural diagram of terminal provided by the invention.As shown in figure 11, the terminal of the present embodiment can be with
Include:
Memory 1101, for storing program instruction.
Processor 1102 realizes terminal side in any of the above-described embodiment of the method for being performed in described program instruction
Step, specific implementation principle can be found in above-described embodiment.
The present invention provides a kind of computer readable storage medium, is stored thereon with computer program, the computer program
The step of server side in any of the above-described embodiment of the method is realized when being executed by processor.
The present invention provides a kind of computer readable storage medium, is stored thereon with computer program, the computer program
The step of terminal side in any of the above-described embodiment of the method is realized when being executed by processor.
The present invention also provides a kind of program product, described program product includes computer program, and the computer program is deposited
In readable storage medium storing program for executing, at least one processor can read the computer program, institute from the readable storage medium storing program for executing for storage
It states at least one processor execution computer program and makes server side in any of the above-described embodiment of the method for server implementation
The step of.
The present invention also provides a kind of program product, described program product includes computer program, and the computer program is deposited
In readable storage medium storing program for executing, at least one processor can read the computer program, institute from the readable storage medium storing program for executing for storage
It states at least one processor and executes the step that the computer program makes terminal implement terminal side in any of the above-described embodiment of the method
Suddenly.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or logical of device or unit
Letter connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) or processor (English: processor) execute this hair
The part steps of bright each embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory
(English: Read-Only Memory, abbreviation: ROM), random access memory (English: Random Access Memory, letter
Claim: RAM), the various media that can store program code such as magnetic or disk.
In the embodiment of above-mentioned terminal device, it should be appreciated that processor can be central processing unit (English: Central
Processing Unit, referred to as: CPU), it can also be other general processors, digital signal processor (English: Digital
Signal Processor, referred to as: DSP), specific integrated circuit (English: Application Specific Integrated
Circuit, referred to as: ASIC) etc..General processor can be microprocessor or the processor is also possible to any conventional place
Manage device etc..It can be embodied directly in hardware processor in conjunction with the step of method disclosed in the present application and execute completion or use
Hardware and software module combination in reason device execute completion.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (22)
1. a kind of searching method characterized by comprising
At least two effective video frames that server receiving terminal is sent, at least two effective videos frame be the terminal from
It is extracted in the video flowing got, the corresponding shooting angle of each effective video frame is not in at least two effective videos frame
Together;
The server identifies at least two effective videos frame, obtains at least two recognition results, it is described at least
Two effective video frames and at least two recognition result correspond;
The server obtains target identification result according at least two recognition result;
The server is according to the target identification as a result, obtaining search result;
Described search result is sent to the terminal by the server.
2. the method according to claim 1, wherein at least two recognition result has for described at least two
Imitate the corresponding at least two texts description of video frame.
3. according to the method described in claim 2, it is characterized in that, the server according at least two recognition result,
Obtain target identification result, comprising:
The server regard the maximum text description of accounting at least two text description as the target identification result.
4. method according to claim 1-3, which is characterized in that the server is according to the target identification knot
Fruit obtains search result, comprising:
The server searches the search result to match with the target identification result in the database.
5. a kind of searching method characterized by comprising
Terminal obtains video flowing;
The terminal extracts at least two effective video frames from the video flowing, each in at least two effective videos frame
The corresponding shooting angle of effective video frame is different;
At least two effective videos frame is sent to server by the terminal, and at least two effective videos frame is for referring to
Show that the server identifies at least two effective videos frame, obtains at least two recognition results, and according to described
At least two recognition results obtain target identification result;And then according to the target identification as a result, obtaining search result;
The terminal receives and shows the described search result that the server is sent.
6. according to the method described in claim 5, it is characterized in that, the terminal obtains video flowing, comprising:
The terminal shoots to obtain the video flowing by the camera of the terminal.
7. according to the method described in claim 5, it is characterized in that, the terminal obtains video flowing, comprising:
The terminal receives user from the video flowing locally uploaded.
8. according to the described in any item methods of claim 5-7, which is characterized in that the terminal extracted from the video flowing to
Few two effective video frames, comprising:
The terminal obtains the corresponding gyro data of each video frame in the video flowing;
The terminal determines at least two effective videos frame according to the corresponding gyro data of each video frame.
9. according to the method described in claim 8, it is characterized in that, the gyro data includes angle value, described at least two
The difference of the corresponding angle value of two neighboring effective video frame is greater than preset value in a effective video frame.
10. a kind of searcher characterized by comprising
Receiving module, for receiving at least two effective video frames of terminal transmission, at least two effective videos frame is institute
State what terminal was extracted from the video flowing got, the corresponding bat of each effective video frame in at least two effective video frame
Take the photograph angle difference;
Identification module obtains at least two recognition results for identifying at least two effective videos frame, it is described extremely
Few two effective video frames and at least two recognition result correspond;
Processing module, for obtaining target identification result according at least two recognition result;
Module is obtained, is used for according to the target identification as a result, obtaining search result;
Sending module, for described search result to be sent to the terminal.
11. device according to claim 10, which is characterized in that at least two recognition result is described at least two
The corresponding at least two texts description of effective video frame.
12. device according to claim 11, which is characterized in that
The processing module is specifically used for regarding the maximum text description of accounting at least two text description as the mesh
Mark recognition result.
13. the described in any item devices of 0-12 according to claim 1, which is characterized in that
The acquisition module, specifically for searching the search result to match with the target identification result in the database.
14. a kind of searcher characterized by comprising
Module is obtained, for obtaining video flowing;
Extraction module, for extracting at least two effective video frames, at least two effective videos frame from the video flowing
In the corresponding shooting angle of each effective video frame it is different;
Sending module, for at least two effective videos frame to be sent to server, at least two effective videos frame
It is used to indicate the server to identify at least two effective videos frame, obtains at least two recognition results, and root
According at least two recognition result, target identification result is obtained;And then according to the target identification as a result, obtaining search knot
Fruit;
Receiving module, the described search result sent for receiving and showing the server.
15. device according to claim 14, which is characterized in that
The acquisition module shoots to obtain the video flowing specifically for the camera by the terminal.
16. device according to claim 14, which is characterized in that
The acquisition module, specifically for receiving user from the video flowing locally uploaded.
17. the described in any item devices of 4-16 according to claim 1, which is characterized in that
The extraction module, specifically for the corresponding gyro data of video frame each in the acquisition video flowing;According to described
The corresponding gyro data of each video frame, determines at least two effective videos frame.
18. device according to claim 19, which is characterized in that the gyro data includes angle value, it is described at least
The difference of the corresponding angle value of two neighboring effective video frame is greater than preset value in two effective video frames.
19. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
Claim 1-4 described in any item methods are realized when being executed by processor.
20. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
Claim 5-9 described in any item methods are realized when being executed by processor.
21. a kind of server characterized by comprising
Processor;And
Memory, for storing the executable instruction of the processor;
Wherein, the processor is configured to realize that claim 1-4 is described in any item via the executable instruction is executed
Method.
22. a kind of terminal characterized by comprising
Processor;And
Memory, for storing the executable instruction of the processor;
Wherein, the processor is configured to realize that claim 5-9 is described in any item via the executable instruction is executed
Method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811136192.3A CN109522449B (en) | 2018-09-28 | 2018-09-28 | Searching method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811136192.3A CN109522449B (en) | 2018-09-28 | 2018-09-28 | Searching method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109522449A true CN109522449A (en) | 2019-03-26 |
CN109522449B CN109522449B (en) | 2021-11-30 |
Family
ID=65770072
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811136192.3A Active CN109522449B (en) | 2018-09-28 | 2018-09-28 | Searching method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109522449B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101593205A (en) * | 2009-06-24 | 2009-12-02 | 清华大学 | Method for searching three-dimension model based on video |
CN103226822A (en) * | 2013-05-15 | 2013-07-31 | 清华大学 | Medical image stitching method |
US20160063331A1 (en) * | 2014-09-02 | 2016-03-03 | Novatek Microelectronics Corp. | Vehicle event data recorder and operation method thereof |
CN105975570A (en) * | 2016-05-04 | 2016-09-28 | 深圳市至壹科技开发有限公司 | Geographic position-based video search method and system |
US20160309087A1 (en) * | 2013-03-15 | 2016-10-20 | Voke Inc. | System and method for generating a plurality of unique videos of a same event |
CN106598998A (en) * | 2015-10-20 | 2017-04-26 | 北京奇虎科技有限公司 | Information acquisition method and information acquisition device |
CN106815237A (en) * | 2015-11-30 | 2017-06-09 | 北京睿创投资管理中心(有限合伙) | Searching method, searcher, user terminal and search server |
US20170228683A1 (en) * | 2014-08-04 | 2017-08-10 | Beijing Didi Infinity Technology And Development Co., Ltd. | Methods and systems for distributing orders |
CN107943837A (en) * | 2017-10-27 | 2018-04-20 | 江苏理工学院 | A kind of video abstraction generating method of foreground target key frame |
US20180176462A1 (en) * | 2013-09-15 | 2018-06-21 | Mediatek Inc. | Method and apparatus for performing image processing operation based on frame/algorithm selection |
CN108449577A (en) * | 2018-03-26 | 2018-08-24 | 成都合能创越软件有限公司 | The gathering method of large capacity consecutive image |
-
2018
- 2018-09-28 CN CN201811136192.3A patent/CN109522449B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101593205A (en) * | 2009-06-24 | 2009-12-02 | 清华大学 | Method for searching three-dimension model based on video |
US20160309087A1 (en) * | 2013-03-15 | 2016-10-20 | Voke Inc. | System and method for generating a plurality of unique videos of a same event |
CN103226822A (en) * | 2013-05-15 | 2013-07-31 | 清华大学 | Medical image stitching method |
US20180176462A1 (en) * | 2013-09-15 | 2018-06-21 | Mediatek Inc. | Method and apparatus for performing image processing operation based on frame/algorithm selection |
US20170228683A1 (en) * | 2014-08-04 | 2017-08-10 | Beijing Didi Infinity Technology And Development Co., Ltd. | Methods and systems for distributing orders |
US20160063331A1 (en) * | 2014-09-02 | 2016-03-03 | Novatek Microelectronics Corp. | Vehicle event data recorder and operation method thereof |
CN106598998A (en) * | 2015-10-20 | 2017-04-26 | 北京奇虎科技有限公司 | Information acquisition method and information acquisition device |
CN106815237A (en) * | 2015-11-30 | 2017-06-09 | 北京睿创投资管理中心(有限合伙) | Searching method, searcher, user terminal and search server |
CN105975570A (en) * | 2016-05-04 | 2016-09-28 | 深圳市至壹科技开发有限公司 | Geographic position-based video search method and system |
CN107943837A (en) * | 2017-10-27 | 2018-04-20 | 江苏理工学院 | A kind of video abstraction generating method of foreground target key frame |
CN108449577A (en) * | 2018-03-26 | 2018-08-24 | 成都合能创越软件有限公司 | The gathering method of large capacity consecutive image |
Non-Patent Citations (1)
Title |
---|
林玲鹏: ""融合前景判别和圆形搜索的目标跟踪算法"", 《计算机应用》 * |
Also Published As
Publication number | Publication date |
---|---|
CN109522449B (en) | 2021-11-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105518678B (en) | Searching method, searcher and user equipment | |
EP2124159B1 (en) | Image learning, automatic annotation, retrieval method, and device | |
CN108833942A (en) | Video cover choosing method, device, computer equipment and storage medium | |
WO2016184051A1 (en) | Picture search method, apparatus and device, and non-volatile computer storage medium | |
CN110427859A (en) | A kind of method for detecting human face, device, electronic equipment and storage medium | |
CN104899306B (en) | Information processing method, information display method and device | |
CN105512180B (en) | A kind of search recommended method and device | |
CN107330040B (en) | Learning question searching method and system | |
CN105956096B (en) | Topic method for fast searching and device based on mobile terminal | |
TWI651673B (en) | Seraching method for product photograph and searching system for product photograph | |
CN103945234A (en) | Video-related information providing method and device | |
JP2017535850A5 (en) | ||
CN106407358A (en) | Image searching method and device and mobile terminal | |
CN110969090A (en) | Fruit quality identification method and device based on deep neural network | |
CN107168536A (en) | Examination question searching method, examination question searcher and electric terminal | |
CN106303235A (en) | Take pictures processing method and processing device | |
CN109189972A (en) | A kind of target whereabouts determine method, apparatus, equipment and computer storage medium | |
CN109961103A (en) | The training method of Feature Selection Model, the extracting method of characteristics of image and device | |
CN104901939B (en) | Method for broadcasting multimedia file and terminal and server | |
JP6822484B2 (en) | Information processing equipment, information processing methods and programs | |
CN109522449A (en) | Searching method and device | |
CN108833989A (en) | A kind of method and apparatus that barrage is generated and shown | |
CN108334852A (en) | A kind of image analysis identifying system and image analysis recognition methods | |
CN103927341B (en) | A kind of method and device for obtaining scene information | |
CN106202360A (en) | Examination question searching method and device |
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 |