CN106570466A - Video classification method and system - Google Patents
Video classification method and system Download PDFInfo
- Publication number
- CN106570466A CN106570466A CN201610937282.7A CN201610937282A CN106570466A CN 106570466 A CN106570466 A CN 106570466A CN 201610937282 A CN201610937282 A CN 201610937282A CN 106570466 A CN106570466 A CN 106570466A
- Authority
- CN
- China
- Prior art keywords
- video
- video file
- case
- information
- packet
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The invention relates to a video classification method and system. Video files within the same preset time period are deemed to be corresponding to one same case and are stored in a same data group, thereby realizing first grouping of the video files; furthermore, based on position information, the video files having the same position information in case video groups are stored in a same data subgroup, thereby realizing second grouping; and besides, the video files are ranked according to time sequence in position video groups, thereby realizing ordered management of all video files. The video classification method and system realize automatic classification of the video files, thereby avoiding the original case of realizing screening by opening the video files one by one by workers, and improving efficiency.
Description
Technical field
The present invention relates to video processing technique, more particularly to a kind of video classification methods and system.
Background technology
With the construction of video investigation troop, case occurs backsight detects personnel needs case-involving videos a large amount of to front end society face
It is acquired.At present, emerged in large numbers it is various provide networking download, hard disk to copying, screen recording, video playback and transcoding, video pluck
The video resource for waiting function gathers individual soldier's equipment.The video for collecting need to achieve a butt joint with video investigation operation system, so as to
In access.
But, by the different modes video council that receives of collection than relatively decentralized, cause video resource organization and administration occur mixed
Disorderly.When being docked, need that first the video for collecting is classified.At present, conventional mode classification is artificial viewing video
Content carries out manual classification.Watched by clicking on video one by one, with reference to video content and personal experience dividing for video is completed
Class, including the ownership of case, the video camera belonging to video and position, time period of video record etc..
However, this kind of mode classification is loaded down with trivial details uninteresting, can greatly increase the workload depending on detecing personnel so that efficiency is very low.
With the explosive growth of video resource, which can not be well adapted for current demand.
The content of the invention
Based on this, it is necessary to for the less efficient problem of visual classification, there is provided a kind of visual classification efficiency that improves
Video classification methods and system.
A kind of video classification methods, including step:
Scanning memorizer, searches video file;
The temporal information of the video file is obtained, and the video file in same preset time period is put under same
In packet, at least one case video group is obtained;
The positional information of the video file is obtained, and identical bits confidence will be included in each described case video group respectively
The video file of breath is put under in corresponding same subdata packet, obtains at least one position video group;
According to the temporal information, the video file in the position video group is ranked up in chronological order.
Wherein in one embodiment, in the temporal information for obtaining the video file, and will be in same default
Video file in time period is put under in same packet, obtain at least one case video group the step of after, also include
Step:
Operational order is obtained, and the video file in the case video group is deleted according to the operational order
And/or merge.
Wherein in one embodiment, in the temporal information for obtaining the video file, and will be in same default
Video file in time period is put under in same packet, obtain at least one case video group the step of after, also include
Step:
Case information is obtained, and the corresponding packet of the case video group is ordered using the case information
Name.
Wherein in one embodiment, the positional information for obtaining the video file, and respectively by each case
The video file comprising same position information is put under in corresponding same subdata packet in part video group, obtains at least one
The step of putting video group includes:
Obtain and preset in the video file sectional drawing of frame, and extract the background information of the sectional drawing as video text
The positional information of part;
The background information of the video file in the case video group is contrasted, by the matching degree of the background information
Put under in same subdata packet more than or equal to the video file of threshold value, obtain the position video group.
Wherein in one embodiment, the positional information for obtaining the video file, and respectively by each case
The video file comprising same position information is stored in corresponding same subdata packet in part video group, obtains at least one
The step of position video group, also includes:
The station location marker in the background information is recognized, and it is corresponding to the position video group using the station location marker
Subdata packet is named.
A kind of video classification system, including:
Scan module, for scanning memorizer, searches video file;
Time packet module, for obtaining the temporal information of the video file, and will be in same preset time period
Video file put under in same packet, obtain at least one case video group;
Position grouping module, for obtaining the positional information of the video file, and respectively by each case video
The video file comprising same position information is put under in corresponding same subdata packet in group, obtains at least one position video
Group;
Order module, for according to the temporal information, by the video file in the position video group in chronological order
It is ranked up.
Wherein in one embodiment, the time packet module includes screening unit, and the screening unit is used to obtain
Operational order, and according to the operational order video file in the case video group is deleted and/or merged.
Wherein in one embodiment, the time packet module includes the first name unit, the first name unit
For obtaining case information, and the corresponding packet of the case video group is named using the case information.
Wherein in one embodiment, the position grouping module includes:
Extraction unit, for obtaining video file in preset the sectional drawing of frame, and extract the background information conduct of the sectional drawing
The positional information of the video file;
Comparing unit, for contrasting to the background information of the video file in the case video group, by the back of the body
The matching degree of scape information is put under in same subdata packet more than or equal to the video file of threshold value, obtains the position video
Group.
Wherein in one embodiment, the position grouping module also includes the second name unit, and second name is single
It is first to be used to recognize the station location marker in the background information, and using the station location marker to the corresponding son of the position video group
Packet is named.
Above-mentioned video classification methods and system, are judged to that correspondence is same by the video file in same preset time period
Case, and be stored in same packet, realize being grouped video file for the first time.Further, according to positional information, will
The video file comprising same position information is deposited in same subdata packet in case video group, realizes second point
Group.Also, in the video group of position according to when order video file is ranked up so that all video files realize have
Sequence is managed.Above-mentioned video classification methods and system realize the automatic classification to video file, it is to avoid artificial opening one by one regards
Frequency file is screened, so as to effectively increase efficiency.
Description of the drawings
Fig. 1 is the schematic flow sheet of video classification methods in one embodiment of the invention;
Fig. 2 is the schematic flow sheet of step S130 in video classification methods shown in Fig. 1;
Fig. 3 is the module diagram of video classification system in one embodiment of the invention;
Fig. 4 is the module diagram of time packet module in video classification system shown in Fig. 3;
Fig. 5 is the module diagram of position grouping module in video classification system shown in Fig. 3.
Specific embodiment
For the ease of understanding the present invention, the present invention is described more fully below with reference to relevant drawings.In accompanying drawing
Give the preferred embodiment of the present invention.But, the present invention can be realized in many different forms, however it is not limited to herein
Described embodiment.On the contrary, the purpose for providing these embodiments is to make the understanding to the disclosure more saturating
It is thorough comprehensive.
It should be noted that when element is referred to as " being fixed on " another element, it can directly on another element
Or can also there is element placed in the middle.When an element is considered as " connection " another element, it can be directly connected to
To another element or may be simultaneously present centering elements.Term as used herein " vertical ", " level ", " left side ",
" right side " and similar statement are for illustrative purposes only.
Unless otherwise defined, all of technology used herein and scientific terminology and the technical field for belonging to the present invention
The implication that technical staff is generally understood that is identical.The term for being used in the description of the invention herein is intended merely to description tool
The purpose of the embodiment of body, it is not intended that of the invention in limiting.Term as used herein " and/or " include one or more phases
The arbitrary and all of combination of the Listed Items of pass.
Fig. 1 is referred to, the video classification methods in one embodiment of the invention include step S110~S140.
Step S110, scans memorizer, searches video file.
Specifically, memorizer can be Acquisition Instrument, portable hard drive, USB flash disk or other video acquisitions and storage device.To storage
Device is scanned, and the file for finding the video formats such as RMVB, MP4 is then judged to video file.Further, search corresponding
Data management file, data management file includes the routing information of video file, attribute information etc..
In one embodiment, also included before above-mentioned steps S110:Detection USB is inserted and is removed event, works as detection
During to USB insertion events, start the scanning to memorizer.
Therefore, once there is new storage device to access, the scanning to it can just be started, so as to improve efficiency.It is appreciated that
In other embodiments, also scanning imaging system can be restarted after enabled instruction is obtained.
Step S120, obtains the temporal information of video file, and the video file in same preset time period is drawn
Enter in same packet, obtain at least one case video group.
Specifically, can from extracting time information in the attribute information of video file, including video typing start time point,
By time point and duration.If extracting time information failure, can also enter to the frame of video of video file in dependence information
Row sectional drawing, carries out the extraction of temporal information from sectional drawing.
Video file in same preset time period is considered as the same case (or " event ") of correspondence.Therefore, by it
In putting same packet under, case video group is obtained, can be easy to manage and consult.Specifically, made with earliest initial time
Time shafts are obtained for starting point, is often separated by Preset Time poor (for example, 15 minutes) for a preset time period.If multiple video files
Initial time in the wherein same preset time period, then the plurality of video file is divided into same case video group,
And put under in identical packet.
In one embodiment, after above-mentioned steps S120, also including step:Operational order is obtained, and according to operation
Instruction is deleted and/or merged to the video file in case video group.
Because the persistent period of each particular case is uncontrollable, might not match with the length of preset time period.
Therefore, it is possible to cause the corresponding video file of same case to be divided into different case video groups, difference is stored respectively in
Packet in.And the video file corresponding to different cases is divided into same case video group, same number is stored in
According in packet.Therefore, after the completion of the packet of case video group, also need further to be screened.
Specifically, operational order includes deleting instruction, merges instruction.User passes through to consult regarding in each case video group
Frequency file, when the corresponding same case of different case video groups or associated case is found, then interacts with operation interface
Produce and merge instruction.When exist in finding case video group video file and current case not to it is corresponding when then with operation interface friendship
Mutually produce and delete instruction.
After obtaining operational order, different case video groups are merged, or will be specific in some case video groups
Video file is deleted, so that the packet of case video group is more accurate.
In one embodiment, after above-mentioned steps S120, also including step:Case information is obtained, and adopts case
Information is named to the corresponding packet of case video group.
Specifically, case information can be obtained from the routing information of video file, is generally comprised to case in routing information
Name.Case information at least includes title of a cause.For example, " case one ", " case two ".If obtain from routing information losing
Lose, then can also pass through the naming operation for obtaining user, realize the artificial setting to case video group name.
The corresponding packet of case video group is named, user can be further facilitated to the corresponding video text of case
Part is consulted and managed.
Step S130, obtains the positional information of video file, and same position will be included in each case video group respectively
The video file of information is put under in corresponding same subdata packet, obtains at least one position video group.
Specifically, positional information can be extracted from the attribute information of video file.If extracting position letter in dependence information
Breath failure, can also carry out sectional drawing to the frame of video of video file, be extracted from sectional drawing.
Positional information identical video file, represents and is shot by the video camera of same position, can reflect the position case
The scene of generation.But, the spot of same merit may be many places.Therefore, by the video file of the same case of correspondence according to
The position difference that case occurs is grouped, and can be easy to from multi-angle be analyzed case.
Video file can be stored in corresponding packet.Additionally, also can by other means realize dividing for data
Group.For example, add corresponding by way of video file is associated with corresponding packet or to video file
Mode of packet name etc..Wherein, packet can be realized in the form of file.So, deposit position video
The file of group is the sub-folder under the folder content of storage correspondence case video group.Under one case video group, can wrap
Include multiple position video groups.Therefore, it is capable of achieving to realize video file layering storage and shows so that the degree of order of video file
It is higher.
After the completion of video file classification, can be easy to be docked with other business platforms (for example, image investigation platform).Depending on
Frequency file can pack upload, packet upload, realize batch processing.And, for different business platforms, call different ports
Agreement, so as to realize easily docking with multiple business platform.
As shown in Fig. 2 in one embodiment, above-mentioned steps S130 include step S131~S133:
Step S131, obtains and preset in video file the sectional drawing of frame, and extracts the background information of sectional drawing as video file
Positional information.
Specifically, the sectional drawing of first frame, intermediate frame and last frame of video file is obtained, and extracts the background of sectional drawing
Information.Intermediate frame can be the arbitrary frame of video between the first frame and last frame.The sectional drawing of three different video frames is obtained, and
By average quantization process, the impact of non-background parts is can remove.Wherein, the shooting of video file is can determine that by background information
Position, thus can using the background information extracted as video file positional information.
Step S133, contrasts to the background information of the video file in case video group, by the matching of background information
Degree is stored in same subdata packet more than or equal to the video file of threshold value, obtains position video group.
Further, the background information that previous step is obtained is carried out into collision and compares analysis.The essence of collision relative analyses is just
It is to subtract each other the background information after quantization, difference then represents that matching degree is more than or equal to threshold value in preset range.If multiple regard
The matching degree of the sectional drawing background information of frequency file is more than or equal to threshold value, then it represents that the background of the plurality of video file is similar, and
Judge that the plurality of video file is same shot by camera.Therefore, the position video being stored in a sub- packet
Group, comprising the video file for same shot by camera.
There is such case:Same position is laid with multiple video cameras.Therefore, if based on location information (CPS positioning, nothing
Line architecture) positional information is obtained, even if then positional information identical video file, it is also possible to by multiple different shootings
Head is captured.Because different photographic head has different shooting angle, therefore can also there is difference in the visual angle of the video file for obtaining
Not.Therefore, this can make the video file comprising multiple visual angles in the video group of position.When user carries out case analysis, position is consulted
During video file in video group, visual angle can repeatedly irregular switching, so as to be unfavorable for observation analysis.
And, as the positional information of video file, and the similar video file of background is divided into together by using background information
One position video group, the then video file for same shot by camera included in same position video group.Therefore, use
Family consult same position video group video file when, visual angle will not frequent switching, consequently facilitating observation analysis.
In one embodiment, above-mentioned steps S130 also include:Station location marker in identification background information, and adopt position
Mark is named to the corresponding subdata packet of position video group.
Specifically, station location marker can be place name, section title and numbering, or the numbering of video camera.Additionally, can also obtain
The position naming operation at family is taken, the artificial setting of position video group name is realized.
Video group corresponding subdata packet in position is named, user can be further facilitated video file is looked into
Read and manage.
Step S140, according to temporal information, the video file in the video group of position is ranked up in chronological order.
Specifically, according to video typing start time point, by time point and duration, complete video file and when
Between the association put, make video file in the video group of position be ranked up displaying by the time sequencing for shooting.Therefore, when position regards
When video file in frequency group is played successively, it is obtained that plot is complete, continuous video content, so as to be conducive to the case to case
Feelings are analyzed.
Above-mentioned video classification methods, by the video file in same preset time period the same case of correspondence is judged to,
And be stored in same packet, realize being grouped video file for the first time.Further, according to positional information, by case
The video file comprising same position information is deposited in same subdata packet in video group, realizes second being grouped.And
And, in the video group of position according to when order video file is ranked up so that all video files realize in order pipe
Reason.Above-mentioned video classification methods realize the automatic classification to video file, it is to avoid artificial video file of opening one by one is carried out
Screening, so as to effectively increase efficiency.
Additionally, the present invention also provides a kind of video classification system.
Fig. 3 is referred to, the video classification system in one embodiment of the invention includes scan module 110, time packet mould
Block 120, position grouping module 130 and order module 140.
Scan module 110 is used to scan memorizer, searches video file.
Specifically, memorizer can be Acquisition Instrument, portable hard drive, USB flash disk or other video acquisitions and storage device.Scanning mould
Block 110 is scanned to memorizer, and the file for finding the video formats such as RMVB, MP4 is then judged to video file.Further
, scan module 110 searches corresponding data management file, and data management file includes the routing information of video file, category
Property information etc..
In one embodiment, scan module 110 was additionally operable to detect USB insertions and removed before carrying out to memorizer
Event, when USB insertion events are detected, starts the scanning to memorizer.
Therefore, once there is new storage device to access, scan module 110 just can start the scanning to it, so as to improve effect
Rate.It is appreciated that in other embodiments, scan module 110 also can restart scanning imaging system after enabled instruction is obtained.
Time packet module 120 is used to obtain the temporal information of video file, and by same preset time period
Video file is put under in same packet, obtains at least one case video group.
Specifically, time packet module 120 can be from extracting time information in the attribute information of video file, including video is recorded
The start time point that enters, by time point and duration.If extracting time information failure, time packet mould in dependence information
Block 120 can also carry out sectional drawing to the frame of video of video file, and the extraction of temporal information is carried out from sectional drawing.
Video file in same preset time period is considered as the same case (or " event ") of correspondence.Therefore, the time
Grouping module 120 is put under in same packet, obtains case video group, can be easy to manage and consult.Specifically, with most
Early initial time obtains time shafts as starting point, is often separated by Preset Time poor (for example, 15 minutes) for a preset time period.
If in wherein same preset time period, the plurality of video file is divided into together the initial time of multiple video files
One case video group, and put under in identical packet.
Fig. 4 is seen also, in one embodiment, time packet module 120 includes screening unit 121, screening unit
121 are used to obtain operational order, and according to operational order the video file in case video group are deleted and/or merged.
Because the persistent period of each particular case is uncontrollable, might not match with the length of preset time period.
Therefore, it is possible to cause the corresponding video file of same case to be divided into different case video groups, difference is stored respectively in
Packet in.And the video file corresponding to different cases is divided into same case video group, same number is stored in
According in packet.Therefore, after the completion of the packet of case video group, also need further to be screened.
Specifically, operational order includes deleting instruction, merges instruction.User passes through to consult regarding in each case video group
Frequency file, when the corresponding same case of different case video groups or associated case is found, then interacts with operation interface
Produce and merge instruction.When exist in finding case video group video file and current case not to it is corresponding when then with operation interface friendship
Mutually produce and delete instruction.
Screening unit 121 is obtained after operational order, and different case video groups are merged, or by some case videos
Particular video file in group is deleted, so that the packet of case video group is more accurate.
In one embodiment, time packet module 120 includes the first name unit 123, and the first name unit 123 is used for
Case information is obtained, and the corresponding packet of case video group is named using case information.
Specifically, the first name unit 123 can obtain case information from the routing information of video file, in routing information
Generally comprise the name to case.Case information at least includes title of a cause.For example, " case one ", " case two ".If from path
Failure is obtained in information, then the first name unit 123 can also pass through the naming operation for obtaining user, realize to case video group name
The artificial setting for claiming.
The corresponding packet of case video group is named, user can be further facilitated to the corresponding video text of case
Part is consulted and managed.
Position grouping module 130 is used to obtain the positional information of video file, and will wrap in each case video group respectively
Video file containing same position information is put under in corresponding same subdata packet, obtains at least one position video group.
Specifically, position grouping module 130 can extract positional information from the attribute information of video file.If dependence is believed
Positional information failure is extracted in breath, position grouping module 130 can also carry out sectional drawing, enter from sectional drawing to the frame of video of video file
Row is extracted.
Positional information identical video file, represents and is shot by the video camera of same position, can reflect the position case
The scene of generation.But, the spot of same merit may be many places.Therefore, by the video file of the same case of correspondence according to
The position difference that case occurs is grouped, and can be easy to from multi-angle be analyzed case.
Video file can be stored in corresponding packet.Additionally, also can by other means realize dividing for data
Group.For example, add corresponding by way of video file is associated with corresponding packet or to video file
Mode of packet name etc..Wherein, packet can be realized in the form of file.So, deposit position video
The file of group is the sub-folder under the folder content of storage correspondence case video group.Under one case video group, can wrap
Include multiple position video groups.Therefore, layering storage can be realized to video file and is shown so that the degree of order of video file is more
It is high.
After the completion of video file classification, can be easy to be docked with other business platforms (for example, image investigation platform).Depending on
Frequency file can pack upload, packet upload, realize batch processing.And, for different business platforms, call different ports
Agreement, so as to realize easily docking with multiple business platform.
Fig. 5 is seen also, in one embodiment, position grouping module 130 includes extraction unit 131 and comparing unit
133。
Extraction unit 131 is used to obtain and preset in video file the sectional drawing of frame, and extracts the background information of sectional drawing as regarding
The positional information of frequency file.
Specifically, extraction unit 131 obtains the sectional drawing of first frame, intermediate frame and last frame of video file, and extracts
Go out the background information of sectional drawing.Intermediate frame can be the arbitrary frame of video between the first frame and last frame.Obtain three differences to regard
The sectional drawing of frequency frame, and by average quantization process, can remove the impact of non-background parts.Wherein, can determine that by background information
The camera site of video file, thus can using the background information extracted as video file positional information.
Comparing unit 133 is used to contrast the background information of the video file in case video group, by background information
Matching degree be stored in the packet of same subdata more than or equal to the video file of threshold value, obtain position video group.
Further, the background information that previous step is obtained is carried out collision and compares analysis by comparing unit 133.Collision is to score
The essence of analysis is exactly to subtract each other the background information after quantization, and difference then represents that matching degree is more than or equal to threshold in preset range
Value.If the matching degree of the sectional drawing background information of multiple video files is more than or equal to threshold value, then it represents that the plurality of video file
Background is similar, and comparing unit 133 then judges that the plurality of video file is same shot by camera.Therefore, it is stored in one
Subdata packet in position video group, comprising the video file for same shot by camera.
There is such case:Same position is laid with multiple video cameras.Therefore, if based on location information (CPS positioning, nothing
Line architecture) positional information is obtained, even if then positional information identical video file, it is also possible to by multiple different shootings
Head is captured.Because different photographic head has different shooting angle, therefore can also there is difference in the visual angle of the video file for obtaining
Not.Therefore, this can make the video file comprising multiple visual angles in the video group of position.When user carries out case analysis, position is consulted
During video file in video group, visual angle can repeatedly irregular switching, so as to be unfavorable for observation analysis.
And, as the positional information of video file, and the similar video file of background is divided into together by using background information
One position video group, the then video file for same shot by camera included in same position video group..Therefore,
User consult same position video group video file when, visual angle will not frequent switching, consequently facilitating observation analysis.
In one embodiment, position grouping module 130 also includes the second name unit 135.Second name unit 135 is used
Station location marker in identification background information, and video group corresponding subdata packet in position is ordered using station location marker
Name.
Specifically, station location marker can be place name, section title and numbering, or the numbering of video camera.Additionally, the second life
Name unit 135 can also obtain the position naming operation of user, realize the artificial setting of position video group name.
Video group corresponding subdata packet in position is named, user can be further facilitated video file is looked into
Read and manage.
Order module 140 is used for according to temporal information, and the video file in the video group of position is arranged in chronological order
Sequence.
Specifically, order module 140 is completed according to the start time point of video typing, by time point and duration
Video file is associated with time point, makes the video file in the video group of position be ranked up displaying by the time sequencing for shooting.
Therefore, when the video file in the video group of position is played successively, it is obtained that plot is complete, continuous video content, so as to have
It is analyzed beneficial to the merit to case.
Above-mentioned video classification system, time packet module 120 judges the video file in same preset time period
To correspond to same case, and it is stored in same packet, realizes being grouped video file for the first time.Further, position
Grouping module 130 is deposited in the video file comprising same position information in case video group same according to positional information
In subdata packet, realize second being grouped.Also, order module 140 in the video group of position according to when order to video text
Part is ranked up, so that all video files realize orderly management.Above-mentioned video classification system is realized to video file
Automatic classification, it is to avoid artificial video file of opening one by one is screened, so as to effectively increasing efficiency.
Each technical characteristic of embodiment described above can be combined arbitrarily, to make description succinct, not to above-mentioned reality
Apply all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, the scope of this specification record is all considered to be.
Embodiment described above only expresses the several embodiments of the present invention, and its description is more concrete and detailed, but and
Can not therefore be construed as limiting the scope of the patent.It should be pointed out that for one of ordinary skill in the art comes
Say, without departing from the inventive concept of the premise, some deformations and improvement can also be made, these belong to the protection of the present invention
Scope.Therefore, the protection domain of patent of the present invention should be defined by claims.
Claims (10)
1. a kind of video classification methods, it is characterised in that including step:
Scanning memorizer, searches video file;
The temporal information of the video file is obtained, and puts the video file in same preset time period under same data
In packet, at least one case video group is obtained;
The positional information of the video file is obtained, and same position information will be included in each described case video group respectively
Video file is put under in corresponding same subdata packet, obtains at least one position video group;
According to the temporal information, the video file in the position video group is ranked up in chronological order.
2. video classification methods according to claim 1, it is characterised in that in the time for obtaining the video file
Information, and the video file in same preset time period is put under in same packet, obtain at least one case and regard
After the step of frequency is organized, also including step:
Obtain operational order, and the video file in the case video group is deleted according to the operational order and/or
Merge.
3. video classification methods according to claim 1, it is characterised in that in the time for obtaining the video file
Information, and the video file in same preset time period is put under in same packet, obtain at least one case and regard
After the step of frequency is organized, also including step:
Case information is obtained, and the corresponding packet of the case video group is named using the case information.
4. video classification methods according to claim 1, it is characterised in that the position letter of the acquisition video file
Breath, and will put corresponding same subdata under comprising the video file of same position information in each described case video group respectively
In packet, obtain at least one position video group the step of include:
Obtain and preset in the video file sectional drawing of frame, and extract the background information of the sectional drawing as the video file
Positional information;
The background information of the video file in the case video group is contrasted, the matching degree of the background information is more than
Or put under in same subdata packet equal to the video file of threshold value, obtain the position video group.
5. video classification methods according to claim 4, it is characterised in that the position letter of the acquisition video file
Breath, and will be stored in corresponding same subnumber comprising the video file of same position information in each described case video group respectively
According in packet, also include the step of obtain at least one position video group:
The station location marker in the background information is recognized, and using the station location marker to the corresponding subnumber of the position video group
It is named according to packet.
6. a kind of video classification system, it is characterised in that include:
Scan module, for scanning memorizer, searches video file;
Time packet module, for obtaining the temporal information of the video file, and will be in regarding in same preset time period
Frequency file is put under in same packet, obtains at least one case video group;
Position grouping module, for obtaining the positional information of the video file, and respectively by each described case video group
Video file comprising same position information is put under in corresponding same subdata packet, obtains at least one position video group;
Order module, for according to the temporal information, the video file in the position video group being carried out in chronological order
Sequence.
7. video classification system according to claim 6, it is characterised in that the time packet module includes that screening is single
Unit, the screening unit is used to obtain operational order, and according to the operational order to the video text in the case video group
Part is deleted and/or merged.
8. video classification system according to claim 6, it is characterised in that the time packet module includes the first name
Unit, the first name unit is used to obtain case information, and using the case information to case video group correspondence
Packet be named.
9. video classification system according to claim 6, it is characterised in that the position grouping module includes:
Extraction unit, for obtaining video file in preset the sectional drawing of frame, and extract the background information of the sectional drawing as described
The positional information of video file;
Comparing unit, for contrasting to the background information of the video file in the case video group, by background letter
The matching degree of breath is put under in same subdata packet more than or equal to the video file of threshold value, obtains the position video group.
10. video classification system according to claim 9, it is characterised in that the position grouping module also includes second
Name unit, described second names unit to be used to recognize the station location marker in the background information, and using the station location marker
The corresponding subdata packet of the position video group is named.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610937282.7A CN106570466B (en) | 2016-11-01 | 2016-11-01 | Video classification method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610937282.7A CN106570466B (en) | 2016-11-01 | 2016-11-01 | Video classification method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106570466A true CN106570466A (en) | 2017-04-19 |
CN106570466B CN106570466B (en) | 2020-09-11 |
Family
ID=58534675
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610937282.7A Active CN106570466B (en) | 2016-11-01 | 2016-11-01 | Video classification method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106570466B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108875062A (en) * | 2018-06-26 | 2018-11-23 | 北京奇艺世纪科技有限公司 | A kind of determination method and device repeating video |
CN108882000A (en) * | 2018-06-27 | 2018-11-23 | 深圳市九洲电器有限公司 | Video interception management method and system |
CN109992679A (en) * | 2019-03-21 | 2019-07-09 | 腾讯科技(深圳)有限公司 | A kind of classification method and device of multi-medium data |
CN110019884A (en) * | 2017-07-28 | 2019-07-16 | 刘谨铭 | A kind of processing method in multiple video source |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102567370A (en) * | 2010-12-27 | 2012-07-11 | 武汉磐大科技有限公司 | Method for quickly searching for videotape fragments |
CN102651020A (en) * | 2012-03-31 | 2012-08-29 | 中国科学院软件研究所 | Method for storing and searching mass sensor data |
CN103853752A (en) * | 2012-11-30 | 2014-06-11 | 国际商业机器公司 | Method and device for managing time series database |
CN104281651A (en) * | 2014-09-16 | 2015-01-14 | 福建星网锐捷安防科技有限公司 | Method and system for searching large volume of video data |
CN104866501A (en) * | 2014-02-24 | 2015-08-26 | 腾讯科技(深圳)有限公司 | Electronic travel photo album generation method and system |
CN105122789A (en) * | 2012-12-12 | 2015-12-02 | 克劳德弗里克公司 | Digital platform for user-generated video synchronized editing |
CN105159976A (en) * | 2015-08-26 | 2015-12-16 | 广东欧珀移动通信有限公司 | Image file processing method and system |
CN105608411A (en) * | 2014-11-19 | 2016-05-25 | 雷尔胡布有限责任公司 | Image classification method and apparatus for preset tour camera |
-
2016
- 2016-11-01 CN CN201610937282.7A patent/CN106570466B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102567370A (en) * | 2010-12-27 | 2012-07-11 | 武汉磐大科技有限公司 | Method for quickly searching for videotape fragments |
CN102651020A (en) * | 2012-03-31 | 2012-08-29 | 中国科学院软件研究所 | Method for storing and searching mass sensor data |
CN103853752A (en) * | 2012-11-30 | 2014-06-11 | 国际商业机器公司 | Method and device for managing time series database |
CN105122789A (en) * | 2012-12-12 | 2015-12-02 | 克劳德弗里克公司 | Digital platform for user-generated video synchronized editing |
CN104866501A (en) * | 2014-02-24 | 2015-08-26 | 腾讯科技(深圳)有限公司 | Electronic travel photo album generation method and system |
CN104281651A (en) * | 2014-09-16 | 2015-01-14 | 福建星网锐捷安防科技有限公司 | Method and system for searching large volume of video data |
CN105608411A (en) * | 2014-11-19 | 2016-05-25 | 雷尔胡布有限责任公司 | Image classification method and apparatus for preset tour camera |
CN105159976A (en) * | 2015-08-26 | 2015-12-16 | 广东欧珀移动通信有限公司 | Image file processing method and system |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110019884A (en) * | 2017-07-28 | 2019-07-16 | 刘谨铭 | A kind of processing method in multiple video source |
CN108875062A (en) * | 2018-06-26 | 2018-11-23 | 北京奇艺世纪科技有限公司 | A kind of determination method and device repeating video |
CN108882000A (en) * | 2018-06-27 | 2018-11-23 | 深圳市九洲电器有限公司 | Video interception management method and system |
CN109992679A (en) * | 2019-03-21 | 2019-07-09 | 腾讯科技(深圳)有限公司 | A kind of classification method and device of multi-medium data |
Also Published As
Publication number | Publication date |
---|---|
CN106570466B (en) | 2020-09-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106570466A (en) | Video classification method and system | |
US8810688B2 (en) | Information processing apparatus and information processing method | |
US8295611B2 (en) | Robust video retrieval utilizing audio and video data | |
CN103258185B (en) | Image processing apparatus, imaging device and image processing method | |
WO2019109643A1 (en) | Video recommendation method and apparatus, and computer device and storage medium | |
CN103207870B (en) | Photo classification management method, server, device and system | |
JP5711387B2 (en) | Method and apparatus for comparing pictures | |
CN102547141B (en) | Method and device for screening video data based on sports event video | |
US20120260175A1 (en) | Method and interface for indexing related media from multiple sources | |
TW200536389A (en) | Intelligent key-frame extraction from a video | |
CN106709424A (en) | Optimized surveillance video storage system and equipment | |
JP5685324B2 (en) | Method and apparatus for comparing pictures | |
CN111131902A (en) | Method for determining target object information and video playing equipment | |
CN102244758A (en) | Video-recording-file-based data acquisition method and equipment | |
CN109348120B (en) | Shooting method, image display method, system and equipment | |
CN104850969A (en) | Warning condition linkage management system for audio and video evidences of law enforcement instrument | |
CN110290346B (en) | Bidding video acquisition method based on intelligent video analysis | |
CN101908057B (en) | Information processing apparatus and information processing method | |
EP3573327B1 (en) | Method and device for displaying target object | |
CN105159959A (en) | Image file processing method and system | |
CN110543584B (en) | Method, device, processing server and storage medium for establishing face index | |
CN112866817B (en) | Video playback method, device, electronic device and storage medium | |
CN103974195A (en) | Pollution source data collection method and system | |
JP2008242965A (en) | Moving image presentation system | |
CN108540817A (en) | Video data handling procedure, device, server and computer readable storage medium |
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 |