CN107861990A - A kind of video searching method and system, terminal device - Google Patents
A kind of video searching method and system, terminal device Download PDFInfo
- Publication number
- CN107861990A CN107861990A CN201710964123.0A CN201710964123A CN107861990A CN 107861990 A CN107861990 A CN 107861990A CN 201710964123 A CN201710964123 A CN 201710964123A CN 107861990 A CN107861990 A CN 107861990A
- Authority
- CN
- China
- Prior art keywords
- search
- video
- present frame
- parameter
- frame
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7847—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using low-level visual features of the video content
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The present invention is applied to video search technique field, there is provided a kind of video searching method and system, terminal device, including：Acquisition judges parameter and scene handoff parameter；Judge whether parameter meets the first preparatory condition, if so, then being scanned for by the first video search pattern to the present frame of current search video；Otherwise judge whether the identification parameter of all decoding blocks of the former frame of present frame meets the second preparatory condition；If the identification parameter of all decoding blocks of the former frame of present frame meets the second preparatory condition, the present frame of current search video is scanned for by the second video search pattern, otherwise judges whether scene handoff parameter meets the 3rd preparatory condition；If scene handoff parameter meets the 3rd preparatory condition, the present frame of current search video is scanned for by the 3rd video search pattern；Otherwise the present frame of current search video is scanned for by the 4th video search pattern, reduces video search operand and improve the validity of video search.
Description
Technical field
The invention belongs to video search technique field, more particularly to a kind of video searching method and system, terminal device.
Background technology
With developing rapidly for multimedia technology and computer networking technology, the main flow that video is increasingly becoming information propagation carries
One of body.It is that people need to solve the problems, such as now that the content of user's needs how is quickly and efficiently searched from video.It is existing
Some video search techniques, the video frequency searching of video content is normally based on, according to the content and context relation of video, automatically
Extract and describe the feature and content of video, then the video data in extensive video database is retrieved.Specifically,
The Video content retrieval based on uncompressed domain and the class of the Video content retrieval based on compression domain two can be divided into.Based on uncompressed domain
All algorithms of Video content retrieval to be carried out on the basis of video content decompresses completely, due in the video that all decompresses
The data volume of appearance is big, thus the operand of Video content retrieval is also very big；And the merely Video content retrieval based on compression domain
The validity of video features can then be reduced.
In summary, there is the problem of operand is big and video features validity is low in existing video searching method.
The content of the invention
In view of this, it is existing to solve the embodiments of the invention provide a kind of video searching method and system, terminal device
In technology there is the problem of operand is big and video features validity is low in video searching method.
The first aspect of the embodiment of the present invention provides a kind of video searching method, including：
Acquisition judges parameter and scene handoff parameter；
Judge it is described judge whether parameter meets the first preparatory condition, if it is described judgement parameter meet the first preparatory condition,
Then the present frame of current search video is scanned for by the first video search pattern；
If the judgement parameter is unsatisfactory for the first preparatory condition, all decoding blocks of the former frame of the present frame are judged
Identification parameter whether meet the second preparatory condition；
If the identification parameter of all decoding blocks of the former frame of the present frame meets the second preparatory condition, pass through second
Video search pattern scans for the present frame of current search video, otherwise, judges whether the scene handoff parameter meets
3rd preparatory condition；
If the scene handoff parameter meets the 3rd preparatory condition, currently searched to described by the 3rd video search pattern
The present frame of rope video scans for；If the scene handoff parameter is unsatisfactory for the 3rd preparatory condition, searched by the 4th video
Rope pattern scans for the present frame of the current search video.
The second aspect of the embodiment of the present invention provides a kind of video searching system, including：
Acquisition module, judge parameter and scene handoff parameter for obtaining；
First judge module, for judge it is described judge whether parameter meets the first preparatory condition, if the judgement parameter
Meet the first preparatory condition, then the present frame of current search video is scanned for by the first video search pattern；
Second judge module, if being unsatisfactory for the first preparatory condition for the judgement parameter, judge the present frame
Whether the identification parameter of all decoding blocks of former frame meets the second preparatory condition；
3rd judge module, if the identification parameter for all decoding blocks of the former frame of the present frame meets that second is pre-
If condition, then the present frame of current search video is scanned for by the second video search pattern, otherwise, judge the scene
Whether handoff parameter meets the 3rd preparatory condition；
4th judge module, if meeting the 3rd preparatory condition for the scene handoff parameter, searched by the 3rd video
Rope pattern scans for the present frame of the current search video；If the scene handoff parameter is unsatisfactory for the 3rd default article
Part, then the present frame of the current search video is scanned for by the 4th video search pattern.
The third aspect of the embodiment of the present invention provides a kind of terminal device, including memory, processor and is stored in
In the memory and the computer program that can run on the processor, described in the computing device during computer program
Realize following steps：
Acquisition judges parameter and scene handoff parameter；
Judge it is described judge whether parameter meets the first preparatory condition, if it is described judgement parameter meet the first preparatory condition,
Then the present frame of current search video is scanned for by the first video search pattern；
If the judgement parameter is unsatisfactory for the first preparatory condition, all decoding blocks of the former frame of the present frame are judged
Identification parameter whether meet the second preparatory condition；
If the identification parameter of all decoding blocks of the former frame of the present frame meets the second preparatory condition, pass through second
Video search pattern scans for the present frame of current search video, otherwise, judges whether the scene handoff parameter meets
3rd preparatory condition；
If the scene handoff parameter meets the 3rd preparatory condition, currently searched to described by the 3rd video search pattern
The present frame of rope video scans for；If the scene handoff parameter is unsatisfactory for the 3rd preparatory condition, searched by the 4th video
Rope pattern scans for the present frame of the current search video.
The fourth aspect of the embodiment of the present invention provides a kind of computer-readable recording medium, the computer-readable storage
Media storage has computer program, and the computer program realizes following steps when being executed by processor：
Acquisition judges parameter and scene handoff parameter；
Judge it is described judge whether parameter meets the first preparatory condition, if it is described judgement parameter meet the first preparatory condition,
Then the present frame of current search video is scanned for by the first video search pattern；
If the judgement parameter is unsatisfactory for the first preparatory condition, all decoding blocks of the former frame of the present frame are judged
Identification parameter whether meet the second preparatory condition；
If the identification parameter of all decoding blocks of the former frame of the present frame meets the second preparatory condition, pass through second
Video search pattern scans for the present frame of current search video, otherwise, judges whether the scene handoff parameter meets
3rd preparatory condition；
If the scene handoff parameter meets the 3rd preparatory condition, currently searched to described by the 3rd video search pattern
The present frame of rope video scans for；If the scene handoff parameter is unsatisfactory for the 3rd preparatory condition, searched by the 4th video
Rope pattern scans for the present frame of the current search video.
Video searching method provided by the invention and system, terminal device, first pass through acquisition and judge parameter and field
Scape handoff parameter, select corresponding video search pattern to scan for all decoding blocks for searching for the present frame of video, enter one
Step ground locking region of search, so that it is determined that target search region, efficiently reduces the operand of video search and improve video and search
The validity of rope.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
In the required accompanying drawing used be briefly described, it should be apparent that, drawings in the following description be only the present invention some
Embodiment, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these
Accompanying drawing obtains other accompanying drawings.
Fig. 1 is a kind of implementation process schematic diagram for video searching method that the embodiment of the present invention one provides；
Fig. 2 is in the step S102 of corresponding embodiment one that the embodiment of the present invention two provides, and passes through the first video search pattern
The implementation process schematic diagram for the step of being scanned for the present frame；
Fig. 3 is in the step S104 of corresponding embodiment one that the embodiment of the present invention three provides, and passes through the second video search pattern
The implementation process schematic diagram for the step of being scanned for the present frame；
Fig. 4 is in the step S105 of corresponding embodiment one that the embodiment of the present invention four provides, and passes through the 3rd video search pattern
The implementation process schematic diagram for the step of being scanned for present frame；
Fig. 5 is in the step S105 of corresponding embodiment one that the embodiment of the present invention five provides, and passes through the 4th video search pattern
The implementation process schematic diagram for the step of being scanned for present frame；
Fig. 6 is a kind of structural representation for video searching system that the embodiment of the present invention six provides；
Fig. 7 is that the first judge module 102 includes being used to perform Fig. 2 in the corresponding embodiment six that the embodiment of the present invention seven provides
The structural representation of method and step in corresponding embodiment；
Fig. 8 is that the 3rd judge module 104 in the corresponding embodiment six that the embodiment of the present invention eight provides includes being used to perform
The structural representation of the method and step in embodiment corresponding to Fig. 3；
Fig. 9 is that the 4th judge module 105 includes being used to perform Fig. 4 in the corresponding embodiment six that the embodiment of the present invention nine provides
The structural representation of method and step in corresponding embodiment；
Figure 10 is that the 4th judge module 105 includes being used for execution figure in the corresponding embodiment six that the embodiment of the present invention ten provides
The structural representation of the method and step in embodiment corresponding to 5；
Figure 11 is the schematic diagram for the terminal device that the embodiment of the present invention 11 provides.
Embodiment
In describing below, in order to illustrate rather than in order to limit, it is proposed that such as tool of particular system structure, technology etc
Body details, thoroughly to understand the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention can also be realized in the other embodiments of details.In other situations, omit to well-known system, device, electricity
Road and the detailed description of method, in case unnecessary details hinders description of the invention.
In order to solve, there is operand greatly in existing video searching method to the embodiment of the present invention and video features validity is low
The problem of, there is provided a kind of video searching method and system, terminal device, first pass through acquisition and judge that parameter and scene are cut
Parameter is changed, selects corresponding video search pattern to scan for all decoding blocks for searching for the present frame of video, further
Region of search is locked, so that it is determined that target search region, efficiently reduces the operand of video search and improve video search
Validity.
In order to illustrate technical solutions according to the invention, illustrated below by specific embodiment.
Embodiment one：
As shown in figure 1, the present embodiment provides a kind of video searching method step, it is specifically included：
Step S101：Acquisition judges parameter and scene handoff parameter.
In one embodiment, step S101 includes：
Pass through formula (1)Acquisition judges parameter；
Pass through formula (2) tpt=sum (sign (bkt(i, j) | condition 2) | 1≤i≤bkh and 1≤j≤bkw), obtain field
Scape handoff parameter；
Wherein, partRepresent the judgement parameter of present frame, tptThe scene handoff parameter of present frame is represented, condition 1 represents to work as
Previous frame is that either present frame is that infra-frame prediction frame or scene handoff parameter meet tp for the first frame of current videot≥0.9*bkh*
Bkw, bktThe i-th row, jth row decoding block in (i, j) expression present frame, bkw represent the row of the decoding block included by present frame
Number, bkh represent the columns of the decoding block included by present frame, and condition 2 represents bkt(i, j) is intra-frame prediction block or present frame
Including at least an intra-frame prediction block.
In the present embodiment, the concrete meaning of formula (1) is：If present frame is the first frame of current video or present frame is
Infra-frame prediction frame or scene handoff parameter meet tpt>=0.9*bkh*bkw, then judge parameter part=1, if not satisfied, then sentencing
Disconnected parameter part=0.The concrete meaning of formula (2) is：The number sum of eligible 2 decoding block in present frame.
Step S102：Judge it is described judge whether parameter meets the first preparatory condition, if it is described judgement parameter meet first
Preparatory condition, then the present frame of current search video is scanned for by the first video search pattern.
In a particular application, the first video search pattern specifically refers to delimit the region of search of present frame, by region of search
Matched with preset search target, search result is obtained according to matching result, and by the division mould of the decoding block that the match is successful
Formula and predictive mode are included in corresponding set respectively.
In a particular application, above-mentioned first preparatory condition is that the judgement parameter is equal to 1, judges that the judgement parameter is
Whether the first preparatory condition of no satisfaction judges described to judge parameter equal to 1.
In step s 103, if the judgement parameter is unsatisfactory for the first preparatory condition, the previous of the present frame is judged
Whether the identification parameter of all decoding blocks of frame meets the second preparatory condition.
In a particular application, when judging that parameter is unsatisfactory for the first preparatory condition, that is, when judging that parameter is not equal to 1, further
Judge whether the identification parameter of all decoding blocks of the former frame of present frame meets the second preparatory condition, wherein, above-mentioned second is pre-
If condition is, the identification parameter of all decoding blocks of the former frame of present frame is all 0.
In step S104, if the identification parameter of all decoding blocks of the former frame of the present frame meets the second default bar
Part, then the present frame of current search video is scanned for by the second video search pattern, otherwise, judge the scene switching
Whether parameter meets the 3rd preparatory condition.
In a particular application, the second video search pattern specifically refers to the identification parameter according to previous decoding block to decoding block
Identification parameter be identified, obtain search result.
In a particular application, above-mentioned 3rd preparatory condition is：0<tpt<0.4*bkh*bkw。
In step S105, if the scene handoff parameter meets the 3rd preparatory condition, pass through the 3rd video search mould
Formula scans for the present frame of the current search video；If the scene handoff parameter is unsatisfactory for the 3rd preparatory condition,
The present frame of the current search video is scanned for by the 4th video search pattern.
In a particular application, whether the 3rd video search pattern refers to is intra-frame prediction block according to decoding block and is
The identification parameter of decoding block is identified with decoding block, search result is obtained according to identification parameter.
In a particular application, the 4th video search pattern refers to whether according to decoding block be intra-frame prediction block to decoding block pair
The identification parameter of decoding block is identified, and search result is obtained according to identification parameter.
In one embodiment, the video searching method also includes：
The initial value of the present frame is set；
If the next frame of the present frame be present, 1 is added to the initial value of the present frame and is arranged to the next frame
The present frame；Otherwise, search is terminated.
In a particular application, 1 is added to the initial value of the present frame and the next frame is arranged to the present frame, specifically
For after the completion of current frame search, continuing using video searching method search next frame.
Video searching method provided by the invention and system, terminal device, first pass through acquisition and judge parameter and field
Scape handoff parameter, select corresponding video search pattern to scan for all decoding blocks for searching for the present frame of video, enter one
Step ground locking region of search, so that it is determined that target search region, efficiently reduces the operand of video search and improve video and search
The validity of rope.
Embodiment two
As shown in Fig. 2 in one embodiment of the invention, in the step S102 in the embodiment corresponding to Fig. 1, pass through
The step of first video search pattern scans for the present frame specifically includes：
Step S201：The field of search of the decoding image of the present frame delimited according to the characteristics of image of preset search target
Domain.
In a particular application, region of search specifically refers to decode some image-region on image, the size of image-region
It can be arranged as required to, specifically, 0 ＜ image-regions≤decoding image.
In a particular application, the primary election for all decoding blocks of the decoding image of present frame being included in current decoding image is searched for
Region, the decoding block of the characteristics of image of search target will not be met, is deleted from the primary election region of search of the decoding image of present frame
Remove, and then get the region of search of current decoding image.
In a particular application, the characteristics of image of above-mentioned search target refers to the rough segmentation characteristics of image for searching for target image, example
Such as characteristics of image such as chromaticity, Texture complications, it is also necessary to which explanation, searching for the characteristics of image of target needs according to specific
Situation is selected, exemplary, when carrying out Face datection, because the target colour of skin contains color characteristics, therefore can will
The decoding block that chrominance information is not met in decoding image is deleted from the primary election region of search of current decoding image, before obtaining
Decode the region of search of image；Exemplary, when carrying out car plate, text detection, because target texture is complicated, therefore can incite somebody to action
Block partition mode is deleted for the decoding block of non-sub-block from the primary election region of search of current decoding image in decoding image, so as to obtain
The region of search of decoding image before taking.
Step S202：Extract the characteristics of image of the region of search and to the characteristics of image of the region of search with it is described pre-
If the characteristics of image of search target is matched.
In a particular application, the characteristics of image of the characteristics of image of region of search and search target is carried out into matching has a variety of realities
Existing mode, is not any limitation as herein.
Step S203：Rower is entered to the identification parameter of all decoding blocks included by the region of search according to matching result
Know, obtain search result.
In a particular application, if the characteristics of image of region of search and the Image Feature Matching of search target, search is regarded
The identification parameter of the decoding block of frequency present frame is identified as 1, and expression region of search is target search region, if the image of region of search
The characteristics of image of feature and search target mismatches, then the identification parameter for the decoding block for searching for video present frame is identified as into 0, table
It is not target search region to show region of search.
Step S204：It is empty set that respectively first set and second set, which assign initial value, by all decoding blocks that the match is successful
Partition mode be included into first set, predictive mode corresponding to all decoding blocks that the match is successful is included into second set.
In a particular application, the partition mode for the current decoding block that all identification parameters are 1 is divided into first set, and
Predictive mode corresponding to decoding block is divided into second set.Exemplary, first set and second set first are assigned into initial value is
Null set, the partition mode for the current decoding block that identification parameter is 1 is divided into first set, and will be predicted corresponding to decoding block
Mode division is second set, that is to say, that first set includes the partition mode of the decoding block of all matching targets, the second collection
Close the predictive mode of the decoding block comprising matching target.
Embodiment three：
As shown in figure 3, in one embodiment of the invention, in the step S104 in the embodiment corresponding to Fig. 1, pass through
The step of second video search pattern scans for the present frame specifically includes：
Step S301：Judge whether the identification parameter of all decoding blocks of the former frame of present frame is all 0.
In a particular application, whether the identification parameter for judging all decoding blocks of former frame is 0, that is, judges former frame
Whether the previous decoding block of decoding block that identification parameter be 1 is not present.
Step S302：If so, the identification parameter for then directly setting all decoding blocks of present frame is 0, search result is obtained, is obtained
To search result.
If the identification parameter of all decoding blocks of former frame is all 0, i.e. the decoding block that identification parameter is 1 is not present in former frame
Previous decoding block, then set present frame whole decoding blocks identification parameter be 0, represent region of search be not target search area
Domain.
Step S303：Otherwise judge whether the scene handoff parameter meets the 3rd preparatory condition.
If the identification parameter of all decoding blocks of former frame is not all 0, i.e. there is the decoding that identification parameter is 1 in former frame
Block, then further select video search pattern to scan for present frame according to scene handoff parameter, that is, judges that scene switches
Whether parameter meets the 3rd preparatory condition.
Example IV：
As shown in figure 4, in one embodiment of the invention, pass through in the step S105 in the embodiment corresponding to Fig. 1
The step of 3rd video search pattern scans for present frame, specifically includes：
Step S401：Meet that " decoding block is the division of intra-frame prediction block and the decoding block by all in present frame
Pattern belongs to first set and the predictive mode of the decoding block belongs to second set " decoding block, be included in region of search.
Step S402：Extract the characteristics of image of the region of search；By the characteristics of image of the region of search and search mesh
Target characteristics of image is matched, and the identification parameter of corresponding decoding block is identified according to matching result.
In a particular application, if the characteristics of image of region of search and the Image Feature Matching of search target, search is regarded
The identification parameter of the decoding block of frequency present frame is identified as 1, and expression region of search is target search region, if the image of region of search
The characteristics of image of feature and search target mismatches, then the identification parameter for the decoding block for searching for video present frame is identified as into 0, table
It is not target search region to show region of search.
Step S403：To the remaining intra-frame prediction block of present frame, then it is 0 to set its identification parameter.
Step S404：To the remaining interframe prediction block of present frame, then the identification that its identification parameter is its reference block is set to join
Numerical value.
Embodiment five：
As shown in figure 5, in one embodiment of the invention, pass through in the step S105 in the embodiment corresponding to Fig. 1
The step of 4th video search pattern scans for present frame, specifically includes：
Step S501：All intra-frame prediction blocks in present frame are included in region of search.
Step S502：Extract the characteristics of image of the region of search；By the characteristics of image of the region of search and search mesh
Target characteristics of image is matched, and the identification parameter of corresponding blocks is identified according to matching result；
In a particular application, if the characteristics of image of region of search and the Image Feature Matching of search target, search is regarded
The identification parameter of the decoding block of frequency present frame is identified as 1, and expression region of search is target search region, if the image of region of search
The characteristics of image of feature and search target mismatches, then the identification parameter for the decoding block for searching for video present frame is identified as into 0, table
It is not target search region to show region of search.
Step S503：To the remaining interframe prediction block of present frame, then the identification that its identification parameter is its reference block is set to join
Numerical value.
Embodiment six
As shown in fig. 6, one embodiment of the present of invention provides a kind of video searching system 100, for performing corresponding to Fig. 1
Embodiment in method and step, it includes：
Acquisition module 101, which is used to obtain, judges parameter and scene handoff parameter.
First judge module 102 be used for judge it is described judge whether parameter meets the first preparatory condition, if it is described judge join
Number meets the first preparatory condition, then the present frame of current search video is scanned for by the first video search pattern.
If the second judge module 103, which is used for the judgement parameter, is unsatisfactory for the first preparatory condition, the present frame is judged
The identification parameter of all decoding blocks of former frame whether meet the second preparatory condition.
If the identification parameter that the 3rd judge module 104 is used for all decoding blocks of the former frame of the present frame meets second
Preparatory condition, then the present frame of current search video is scanned for by the second video search pattern, otherwise, judge the field
Whether scape handoff parameter meets the 3rd preparatory condition.
If the 4th judge module 105 is used for the scene handoff parameter and meets the 3rd preparatory condition, pass through the 3rd video
Search pattern scans for the present frame of the current search video；If the scene handoff parameter is unsatisfactory for the 3rd default article
Part, then the present frame of the current search video is scanned for by the 4th video search pattern.
In one embodiment, the system also includes：
Division module, for the decoding image of present frame to be divided into some rows and several columns decoding block.
Embodiment seven
As shown in fig. 7, in one embodiment of the invention, the first judge module 102 in the embodiment corresponding to Fig. 6
Including the structure for performing the method and step in the embodiment corresponding to Fig. 2, it includes：
Unit 201 delimited in first area, for delimiting the solution of the present frame according to the characteristics of image of preset search target
The region of search of code image.
First matching unit 202, for extracting the characteristics of image of the region of search and to the image of the region of search
Feature is matched with the characteristics of image of the preset search target.
First mark unit 203, for according to knowledge of the matching result to all decoding blocks included by the region of search
Other parameter is identified, and obtains search result.
Gather division unit 204, for being respectively that to assign initial value be empty set for first set and second set, by it is all match into
The partition mode of the decoding block of work(is included into first set, and predictive mode corresponding to all decoding blocks that the match is successful is included into second
Set.
Embodiment eight：
As shown in figure 8, in one embodiment of the invention, the 3rd judge module 104 in the embodiment corresponding to Fig. 6
Including the structure for performing the method and step in the embodiment corresponding to Fig. 3, it includes：
Whether the first judging unit 301, the identification parameter of all decoding blocks of former frame for judging present frame are all 0.
Second mark unit 302, if the identification parameter of all decoding blocks of former frame for present frame is all 0, directly
The identification parameter for setting all decoding blocks of present frame is 0, obtains search result.
Second judging unit 303, if the identification parameter of all decoding blocks of former frame for present frame is not all 0, sentence
Whether the scene handoff parameter that breaks meets the 3rd preparatory condition.
Embodiment nine：
As shown in figure 9, in one embodiment of the invention, the 4th judge module 105 in the embodiment corresponding to Fig. 9
Including the structure for performing the method and step in the embodiment corresponding to Fig. 4, it includes：
Second area delimit unit 401, for meeting that " decoding block is intra-frame prediction block and institute by all in present frame
The partition mode for stating decoding block belongs to first set and the predictive mode of the decoding block belongs to second set " decoding block, draw
Enter region of search.
Second matching unit 402, for extracting the characteristics of image of the region of search；The image of the region of search is special
Levy and matched with searching for the characteristics of image of target, the identification parameter of corresponding decoding block is identified according to matching result.
3rd mark unit 403, for the remaining intra-frame prediction block of present frame, then it to be 0 to set its identification parameter.
4th mark unit 404, for the remaining interframe prediction block of present frame, then setting its identification parameter to be referred to for it
The identification parameter value of block.
Embodiment ten：
As shown in Figure 10, in one embodiment of the invention, the 4th judge module in the embodiment corresponding to Figure 10
105 include being used for the structure for performing the method and step in the embodiment corresponding to Fig. 5, and it includes：
3rd regional assignment unit 501, for all intra-frame prediction blocks in present frame to be included in into region of search.
3rd matching unit 502, for extracting the characteristics of image of the region of search；The image of the region of search is special
Levy and matched with searching for the characteristics of image of target, the identification parameter of corresponding blocks is identified according to matching result.
5th mark unit 503, for the remaining interframe prediction block of present frame, then setting its identification parameter to be referred to for it
The identification parameter value of block.
Embodiment 11：
Figure 11 is the schematic diagram for the terminal device that one embodiment of the invention provides.As shown in figure 11, the terminal of the embodiment
Equipment 11 includes：Processor 110, memory 111 and it is stored in the memory 111 and can be on the processor 110
The computer program 112 of operation, such as program.The processor 110 is realized above-mentioned each when performing the computer program 112
Step in video searching method embodiment, such as step 101 shown in Fig. 1 is to 105.Or the processor 110 performs institute
The function of each module/unit in above-mentioned video searching system embodiment, such as mould shown in Fig. 6 are realized when stating computer program 112
The function of block 101 to 105.
Exemplary, the computer program 112 can be divided into one or more module/units, it is one or
Multiple module/the units of person are stored in the memory 111, and are performed by the processor 110, to complete the present invention.Institute
It can be the series of computation machine programmed instruction section that can complete specific function to state one or more module/units, the instruction segment
For describing implementation procedure of the computer program 112 in the terminal device 11.For example, the computer program 112
Acquisition module, the first judge module, the second judge module, the 3rd judge module and the 4th judge module can be divided into,
Each module concrete function is as follows：
Acquisition module, judge parameter and scene handoff parameter for obtaining；
First judge module, for judge it is described judge whether parameter meets the first preparatory condition, if the judgement parameter
Meet the first preparatory condition, then the present frame of current search video is scanned for by the first video search pattern；
Second judge module, if being unsatisfactory for the first preparatory condition for the judgement parameter, judge the present frame
Whether the identification parameter of all decoding blocks of former frame meets the second preparatory condition；
3rd judge module, if the identification parameter for all decoding blocks of the former frame of the present frame meets that second is pre-
If condition, then the present frame of current search video is scanned for by the second video search pattern, otherwise, judge the scene
Whether handoff parameter meets the 3rd preparatory condition；
4th judge module, if meeting the 3rd preparatory condition for the scene handoff parameter, searched by the 3rd video
Rope pattern scans for the present frame of the current search video；If the scene handoff parameter is unsatisfactory for the 3rd default article
Part, then the present frame of the current search video is scanned for by the 4th video search pattern.
The terminal device 11 can be that the calculating such as desktop PC, notebook, palm PC and cloud server are set
It is standby.The terminal device may include, but be not limited only to, processor 110, memory 111.It will be understood by those skilled in the art that
Figure 11 is only the example of terminal device 11, does not form the restriction to terminal device 11, can be included more more or more than illustrating
Few part, some parts or different parts are either combined, such as the terminal device can also be set including input and output
Standby, network access equipment, bus etc..
Alleged processor 110 can be CPU (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other PLDs, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng.
The memory 111 can be the internal storage unit of the terminal device 11, such as the hard disk of terminal device 11
Or internal memory.The memory 111 can also be the External memory equipment of the terminal device 11, such as on the terminal device 11
The plug-in type hard disk of outfit, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD)
Card, flash card (Flash Card) etc..Further, the memory 111 can also be both interior including the terminal device 11
Portion's memory cell also includes External memory equipment.The memory 111 is used to store the computer program and the terminal
Other programs and data needed for equipment.The memory 111, which can be also used for temporarily storing, have been exported or will be defeated
The data gone out.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each work(
Can unit, module division progress for example, in practical application, can be as needed and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device are divided into different functional units or module, more than completion
The all or part of function of description.Each functional unit, module in embodiment can be integrated in a processing unit, also may be used
To be that unit is individually physically present, can also two or more units it is integrated in a unit, it is above-mentioned integrated
Unit can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.In addition, each function list
Member, the specific name of module are not limited to the protection domain of the application also only to facilitate mutually distinguish.Said system
The specific work process of middle unit, module, the corresponding process in preceding method embodiment is may be referred to, will not be repeated here.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and is not described in detail or remembers in some embodiment
The part of load, it may refer to the associated description of other embodiments.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Member and algorithm steps, it can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, application-specific and design constraint depending on technical scheme.Professional and technical personnel
Described function can be realized using distinct methods to each specific application, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method, can be with
Realize by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, only a kind of division of logic function, there can be other dividing mode when actually realizing, such as
Multiple units or component can combine or be desirably integrated into another system, or some features can be ignored, or not perform.Separately
A bit, shown or discussed mutual coupling or direct-coupling or communication connection can be by some interfaces, device
Or INDIRECT COUPLING or the communication connection of unit, can be electrical, mechanical or other forms.
The unit illustrated as separating component can be or may not be physically separate, show as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated module/unit realized in the form of SFU software functional unit and as independent production marketing or
In use, it can be stored in a computer read/write memory medium.Based on such understanding, the present invention realizes above-mentioned implementation
All or part of flow in example method, by computer program the hardware of correlation can also be instructed to complete, described meter
Calculation machine program can be stored in a computer-readable recording medium, and the computer program can be achieved when being executed by processor
The step of stating each embodiment of the method..Wherein, the computer program includes computer program code, the computer program
Code can be source code form, object identification code form, executable file or some intermediate forms etc..Computer-readable Jie
Matter can include：Can carry any entity or device of the computer program code, recording medium, USB flash disk, mobile hard disk,
Magnetic disc, CD, computer storage, read-only storage (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It is it should be noted that described
The content that computer-readable medium includes can carry out appropriate increasing according to legislation in jurisdiction and the requirement of patent practice
Subtract, such as in some jurisdictions, according to legislation and patent practice, computer-readable medium do not include be electric carrier signal and
Telecommunication signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although with reference to foregoing reality
Example is applied the present invention is described in detail, it will be understood by those within the art that：It still can be to foregoing each
Technical scheme described in embodiment is modified, or carries out equivalent substitution to which part technical characteristic；And these are changed
Or replace, the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical scheme, all should
Within protection scope of the present invention.
Claims (10)
1. a kind of video searching method, it is characterised in that the video searching method includes：
Acquisition judges parameter and scene handoff parameter；
Judge it is described judge whether parameter meets the first preparatory condition, if it is described judgement parameter meet the first preparatory condition, lead to
The first video search pattern is crossed to scan for the present frame of current search video；
If the judgement parameter is unsatisfactory for the first preparatory condition, the knowledge of all decoding blocks of the former frame of the present frame is judged
Whether other parameter meets the second preparatory condition；
If the identification parameter of all decoding blocks of the former frame of the present frame meets the second preparatory condition, pass through the second video
Search pattern scans for the present frame of current search video, otherwise, judges whether the scene handoff parameter meets the 3rd
Preparatory condition；
If the scene handoff parameter meets the 3rd preparatory condition, the current search is regarded by the 3rd video search pattern
The present frame of frequency scans for；If the scene handoff parameter is unsatisfactory for the 3rd preparatory condition, pass through the 4th video search mould
Formula scans for the present frame of the current search video.
2. video searching method according to claim 1, it is characterised in that it is described by the first video search pattern to work as
The present frame of preceding search video scans for, including：
The region of search of the decoding image of the present frame delimited according to the characteristics of image of preset search target；
Extract the characteristics of image of the region of search and the characteristics of image to the region of search and the preset search target
Characteristics of image is matched；
The identification parameter of all decoding blocks included by the region of search is identified according to matching result, obtains search knot
Fruit；
It is empty set that respectively first set and second set, which assign initial value, and the partition mode of all decoding blocks that the match is successful is included into
First set, predictive mode corresponding to all decoding blocks that the match is successful is included into second set.
3. video searching method according to claim 1, it is characterised in that it is described by the second video search pattern to institute
Present frame is stated to scan for, including：
Judge whether the identification parameter of all decoding blocks of former frame of present frame is all 0；
If so, the identification parameter for then directly setting all decoding blocks of present frame is 0, search result is obtained；
Otherwise judge whether the scene handoff parameter meets the 3rd preparatory condition.
4. video searching method according to claim 1, it is characterised in that it is described by the 3rd video search pattern to work as
Previous frame scans for, including：
Meet that " decoding block belongs to the first collection for the partition mode of intra-frame prediction block and the decoding block by all in present frame
Close and the predictive mode of the decoding block belong to second set " decoding block, be included in region of search；
Extract the characteristics of image of the region of search；The characteristics of image of the region of search is entered with searching for the characteristics of image of target
Row matching, the identification parameter of corresponding decoding block is identified according to matching result；
To the remaining intra-frame prediction block of present frame, then it is 0 to set its identification parameter；
To the remaining interframe prediction block of present frame, then the identification parameter value that its identification parameter is its reference block is set.
5. video searching method according to claim 1, it is characterised in that it is described by the 4th video search pattern to work as
Previous frame scans for including：
All intra-frame prediction blocks in present frame are included in region of search；
Extract the characteristics of image of the region of search；The characteristics of image of the region of search is entered with searching for the characteristics of image of target
Row matching, is identified according to matching result to the identification parameter of corresponding blocks；
To the remaining interframe prediction block of present frame, then the identification parameter value that its identification parameter is its reference block is set.
6. a kind of video searching system, it is characterised in that the video searching system includes：
Acquisition module, judge parameter and scene handoff parameter for obtaining；
First judge module, for judge it is described judge whether parameter meets the first preparatory condition, if it is described judgement parameter meet
First preparatory condition, then the present frame of current search video is scanned for by the first video search pattern；
Second judge module, if being unsatisfactory for the first preparatory condition for the judgement parameter, judge the previous of the present frame
Whether the identification parameter of all decoding blocks of frame meets the second preparatory condition；
3rd judge module, if the identification parameter for all decoding blocks of the former frame of the present frame meets the second default bar
Part, then the present frame of current search video is scanned for by the second video search pattern, otherwise, judge the scene switching
Whether parameter meets the 3rd preparatory condition；
4th judge module, if meeting the 3rd preparatory condition for the scene handoff parameter, pass through the 3rd video search mould
Formula scans for the present frame of the current search video；If the scene handoff parameter is unsatisfactory for the 3rd preparatory condition,
The present frame of the current search video is scanned for by the 4th video search pattern.
7. video searching system according to claim 6, its feature with first judge module includes：
Unit delimited in first area, for the decoding image according to the characteristics of image of the preset search target delimitation present frame
Region of search；
First matching unit, for extracting the characteristics of image of the region of search and the characteristics of image to the region of search and institute
The characteristics of image for stating preset search target is matched；
First mark unit, for being entered according to matching result to the identification parameter of all decoding blocks included by the region of search
Line identifier, obtain search result；
Gather division unit, for being respectively that to assign initial value be empty set for first set and second set, by all solutions that the match is successful
The partition mode of code block is included into first set, and predictive mode corresponding to all decoding blocks that the match is successful is included into second set.
8. video searching system according to claim 6, it is characterised in that second judge module includes：
Whether the first judging unit, the identification parameter of all decoding blocks of former frame for judging present frame are all 0；
Second mark unit, if the identification parameter of all decoding blocks of former frame for present frame is all 0, directly set current
The identification parameter of all decoding blocks of frame is 0, obtains search result；
Second judging unit, if the identification parameter of all decoding blocks of former frame for present frame is not all 0, judge the field
Whether scape handoff parameter meets the 3rd preparatory condition.
9. a kind of terminal device, including memory, processor and it is stored in the memory and can be on the processor
The computer program of operation, it is characterised in that realize such as claim 1 to 5 described in the computing device during computer program
The step of any one methods described.
10. a kind of computer-readable recording medium, the computer-readable recording medium storage has computer program, and its feature exists
In when the computer program is executed by processor the step of realization such as any one of claim 1 to 5 methods described.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710964123.0A CN107861990B (en) | 2017-10-17 | 2017-10-17 | Video searching method and system and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710964123.0A CN107861990B (en) | 2017-10-17 | 2017-10-17 | Video searching method and system and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107861990A true CN107861990A (en) | 2018-03-30 |
| CN107861990B CN107861990B (en) | 2020-11-06 |
Family
ID=61698807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710964123.0A Active CN107861990B (en) | 2017-10-17 | 2017-10-17 | Video searching method and system and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107861990B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109873987A (en) * | 2019-03-04 | 2019-06-11 | 深圳市梦网百科信息技术有限公司 | A kind of Target Searching Method and system based on monitor video |
| CN110188166A (en) * | 2019-05-15 | 2019-08-30 | 北京字节跳动网络技术有限公司 | Document search method, device and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050238103A1 (en) * | 2002-08-06 | 2005-10-27 | Raghavan Subramaniyan | Method and apparatus for performing high quality fast predictive motion search |
| CN101339561B (en) * | 2008-08-07 | 2011-12-28 | 北京中星微电子有限公司 | Search method, device and monitoring system for monitoring video frequency image |
| CN106611043A (en) * | 2016-11-16 | 2017-05-03 | 深圳百科信息技术有限公司 | Video searching method and system |
| CN106682094A (en) * | 2016-12-01 | 2017-05-17 | 深圳百科信息技术有限公司 | Human face video retrieval method and system |
-
2017
- 2017-10-17 CN CN201710964123.0A patent/CN107861990B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050238103A1 (en) * | 2002-08-06 | 2005-10-27 | Raghavan Subramaniyan | Method and apparatus for performing high quality fast predictive motion search |
| CN101339561B (en) * | 2008-08-07 | 2011-12-28 | 北京中星微电子有限公司 | Search method, device and monitoring system for monitoring video frequency image |
| CN106611043A (en) * | 2016-11-16 | 2017-05-03 | 深圳百科信息技术有限公司 | Video searching method and system |
| CN106682094A (en) * | 2016-12-01 | 2017-05-17 | 深圳百科信息技术有限公司 | Human face video retrieval method and system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109873987A (en) * | 2019-03-04 | 2019-06-11 | 深圳市梦网百科信息技术有限公司 | A kind of Target Searching Method and system based on monitor video |
| CN110188166A (en) * | 2019-05-15 | 2019-08-30 | 北京字节跳动网络技术有限公司 | Document search method, device and electronic equipment |
| CN110188166B (en) * | 2019-05-15 | 2021-10-15 | 北京字节跳动网络技术有限公司 | Document searching method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107861990B (en) | 2020-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240289647A1 (en) | Knowledge graph processing | |
| CN111858869B (en) | Data matching method and device, electronic equipment and storage medium | |
| CN109785334A (en) | Cardiac magnetic resonance images dividing method, device, terminal device and storage medium | |
| US11347792B2 (en) | Video abstract generating method, apparatus, and storage medium | |
| CN108197285A (en) | A kind of data recommendation method and device | |
| CN107507028A (en) | User preference determines method, apparatus, equipment and storage medium | |
| CN113254669B (en) | Knowledge graph-based power distribution network CIM model information completion method and system | |
| CN112052954B (en) | Gradient lifting tree modeling method and device and terminal | |
| CN110110049A (en) | Service consultation method, device, system, service robot and storage medium | |
| CN111915555B (en) | 3D network model pre-training method, system, terminal and storage medium | |
| CN109299379B (en) | Article recommendation method and device, storage medium and electronic equipment | |
| CN113657289A (en) | Training method and device of threshold estimation model and electronic equipment | |
| CN111652181A (en) | Target tracking method and device and electronic equipment | |
| CN107861990A (en) | A kind of video searching method and system, terminal device | |
| CN108009437A (en) | Data publication method and apparatus and terminal | |
| WO2020199962A1 (en) | Method for improving shelf placement in conventional retail industry | |
| CN111159577B (en) | Community dividing method and device, storage medium and electronic device | |
| CN117830537B (en) | Weak supervision 3D scene graph generation method, device, equipment and medium | |
| CN107066175A (en) | Method and device for generating display interface of securities | |
| CN114553717A (en) | Network node dividing method, device, equipment and storage medium | |
| CN110288465A (en) | Object determines method and device, storage medium, electronic device | |
| CN112270384A (en) | Loop detection method and device, electronic equipment and storage medium | |
| CN107528969A (en) | Management method, managing device and the terminal device of telephone call time | |
| CN107798249A (en) | The dissemination method and terminal device of behavioral pattern data | |
| CN114328792A (en) | Base station site selection method and related equipment for co-building shared network |
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 | ||
| CB02 | Change of applicant information |
Address after: 518000 Guangdong city of Shenzhen province Nanshan District Guangdong streets high in the four Longtaili Technology Building Room 325 No. 30 Applicant after: Shenzhen mengwang video Co., Ltd Address before: 518000 Guangdong city of Shenzhen province Nanshan District Guangdong streets high in the four Longtaili Technology Building Room 325 No. 30 Applicant before: SHENZHEN MONTNETS ENCYCLOPEDIA INFORMATION TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |