CN110781815A - Video data processing method and system - Google Patents
Video data processing method and system Download PDFInfo
- Publication number
- CN110781815A CN110781815A CN201911022529.2A CN201911022529A CN110781815A CN 110781815 A CN110781815 A CN 110781815A CN 201911022529 A CN201911022529 A CN 201911022529A CN 110781815 A CN110781815 A CN 110781815A
- Authority
- CN
- China
- Prior art keywords
- data
- level
- clustering
- merging
- group
- 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
Images
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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to a video data processing method, which is characterized in that a lower system firstly clusters video data in a corresponding clustering range for the first time, the corresponding clustering range of the lower system can be small territory ranges such as county and county, the lower system clusters the video data in the small territory, and the clustering precision is high. And receiving the lower-level clustering data reported by each lower-level system, merging the lower-level clustering data to merge the matched lower-level clustering data of different lower-level systems into the same merging group, and determining the video data in the same merging group as a group of upper-level clustering data. Because each group of superior clustering data is obtained by combining the subordinate clustering data with high clustering precision, the clustering precision of each group of superior clustering data is also higher, namely the data clustering accuracy in a large-scale and massive data environment is improved.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and a system for processing video data.
Background
The intelligent analysis and processing of videos are gradually deepened from the early first generation moving object detection and abstract concentration to the second generation moving object structured classification and then to the third generation classified object identification, and the analysis and application of the moving objects in the video images are deepened. With the increase of user demands and the application pain points of view structured data highlighted, an intelligent analysis technology of fourth-generation video data is coming, namely how to quickly construct massive video data analysis application based on a minimum computing unit, how to cluster and collect massive data targets, and how to provide efficient data service, which will become a mainstream development trend in the future.
The accuracy of the image recognition technology is limited by the existing video object archiving and clustering technology, and when the base number of archiving and clustering calculation is large, the caused archiving and clustering error is amplified. Therefore, the mainstream video image system product at present mainly realizes the archiving and clustering calculation of video objects based on the environment with small area and small data volume, and has poor archiving and clustering accuracy under the environment with large range and mass data.
Disclosure of Invention
To overcome at least some of the problems in the related art, the present application provides a video data processing method and system.
The scheme of the application is as follows:
according to a first aspect of embodiments of the present application, there is provided a video data processing method, including:
receiving lower-level clustering data reported by each lower-level system, wherein the lower-level clustering data are obtained by clustering video data in a corresponding clustering range by each lower-level system, and the number of the lower-level systems is multiple;
merging the lower-level clustering data to merge the matched lower-level clustering data of different lower-level systems into the same merging group;
and determining the video data in the same merge group as a group of upper-level cluster data.
Preferably, in an implementation manner of the present application, before the merging the clustering data, the method further includes:
and acquiring a merging relation table stored in a superior system to merge the clustering data according to the merging relation table, wherein the merging relation table is used for recording associated information, the associated information comprises uniform identification, and different merging groups have different uniform identification.
Preferably, in an implementation manner of the present application, the lower-level cluster data includes a current identifier, and the merging the cluster data according to the merge relationship table includes:
judging whether the current identification exists in the associated information recorded by the combination relation table;
and if so, merging the lower-level clustering data into a merging group corresponding to the unified identification included in the associated information to which the current identification belongs.
Preferably, in an implementable manner of the present application, the method further comprises:
if not, comparing the lower-level clustering data with the data in each merging group, and judging whether data matched with the lower-level clustering data exist or not;
and if the matched data exists, merging the lower-level clustering data into a merging group where the matched data is located.
Preferably, in an implementable manner of the present application, the method further comprises:
if no matched data exists, a merging group is newly established, the lower-level clustering data is merged into the newly established merging group, a unified identification is newly distributed to the merging group, an associated message is newly added in the merging relation table, and the newly added associated relation comprises the newly distributed unified identification.
Preferably, in an implementation manner of the present application, if the merged group has a uniform identifier, after the merging the cluster data, the method further includes:
determining a unified identifier of a merging group into which the lower-level clustering data is merged;
and sending the uniform identifier to a subordinate system from which the subordinate clustered data come, so that the subordinate system uses the uniform identifier to identify the subordinate clustered data in the subordinate system.
Preferably, in an implementable manner of the present application, the current identification is:
a uniform identifier corresponding to the subordinate clustered data, wherein the uniform identifier is obtained by the subordinate system from the superior system before and is used for identifying the subordinate clustered data; alternatively, the first and second electrodes may be,
the lower-level clustering data of different lower-level systems have different lower-level identifications, the associated information further comprises lower-level identifications, and each uniform identification is associated with one or more lower-level identifications.
Preferably, in an implementable manner of the present application, the method further comprises:
and storing or applying the upper-level clustering data in an upper-level system.
According to a second aspect of embodiments of the present application, there is provided a video data processing system, comprising:
each lower system is used for clustering the video data in the corresponding clustering range to obtain corresponding lower clustering data;
the upper-level system is used for receiving the lower-level clustering data and merging the lower-level clustering data, so that the matched lower-level clustering data of different lower-level systems are merged into the same merging group; and determining the video data in the same merge group as a group of upper-level cluster data.
Preferably, in an implementable manner of the present application, the video data processing system further comprises:
and the cascade service system is used for receiving the lower-level clustering data and sending the lower-level clustering data to the upper-level system.
The technical scheme provided by the application can comprise the following beneficial effects:
in the application, the video data in the corresponding clustering range are clustered for the first time through the lower system, the corresponding clustering range of the lower system can be small territory ranges such as counties and villages, the lower system clusters the video data in the small territory, and the clustering precision is high. And receiving the lower-level clustering data reported by each lower-level system, merging the lower-level clustering data to merge the matched lower-level clustering data of different lower-level systems into the same merging group, and determining the video data in the same merging group as a group of upper-level clustering data. Because each group of superior clustering data is obtained by combining the subordinate clustering data with high clustering precision, the clustering precision of each group of superior clustering data is also higher, namely the data clustering accuracy in a large-scale and massive data environment is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
Fig. 1 is a flowchart of a video data processing method according to an embodiment of the present application;
fig. 2 is a flowchart of a video data processing method according to another embodiment of the present application;
fig. 3 is a block diagram of a video data processing system according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
Fig. 1 is a flowchart of a video data processing method according to an embodiment of the present application, and referring to fig. 1, a video data processing method includes:
s11: receiving lower-level clustering data reported by each lower-level system 31, wherein the lower-level clustering data are obtained by clustering the video data in the corresponding clustering range by each lower-level system 31, and a plurality of lower-level systems 31 are provided;
in this embodiment, the video data is a general term, and actually the video data also includes picture data.
The clustering of the video data in the corresponding clustering range by the lower system 31 specifically includes:
and data access to the video stream and the picture stream is realized through the data acquisition module, and the face, the human body and the vehicle snapshot picture and video data are obtained.
And respectively calling face, human body and vehicle structural algorithm services by a structural calculation scheduling engine, inputting snap pictures and videos, and outputting and acquiring corresponding structural information data.
The structural characteristics refer to:
structuring the pedestrian: for people in video images, various structured feature attribute information of pedestrians can be provided, including clothing and ornament features: coats, trousers, skirts and dresses, shoes, hats, sunglasses and sunglasses, scarves and belt waistbands; carrying object characteristics: single shoulder satchels, backpack, handbags, draw-bar boxes, umbrellas; human body characteristics: hair, face.
Vehicle structuring: for the vehicle in the video image, the multi-lane vehicle detection and the head and tail detection and identification functions can be performed, and more than 10 items of structured attribute information of the vehicle can be extracted and identified, including the number plate of the vehicle, the color of the vehicle body, the brand of the vehicle, the type of the vehicle, the sub-brand, the year money of the vehicle and various vehicle feature information, such as: annual inspection mark, sunshading board, pendant, goods of furniture for display rather than for use, paper handkerchief box, safety belt etc..
And calling a video object filing and clustering algorithm, clustering the same portrait and the same vehicle through the location, time and structural characteristics, generating a lower-level identifier corresponding to the lower-level clustering data, and finishing the process of clustering the video data in the corresponding clustering range by the lower-level system 31.
S12: merging the lower-level clustering data to merge the matched lower-level clustering data of different lower-level systems 31 into the same merging group;
before merging the clustered data, referring to fig. 2, the method further includes:
s21: a merging relation table stored in the upper-level system 32 is obtained to merge the cluster data according to the merging relation table, where the merging relation table is used to record associated information, the associated information includes a uniform identifier, and different merging groups have different uniform identifiers.
The merging relation table is used for recording the association information, the association information comprises a uniform identifier, and different merging groups have different uniform identifiers.
For example, the upper system 32 has a small steel data merge group, a small bright data merge group, and a small red data merge group, and the unified identifiers of these three merge groups are small steel data, small bright data, and small red data, respectively.
Wherein the small and rigid data combining group comprises: the data of the small steel uploaded by the lower system 31 in the area a, the data of the small steel uploaded by the lower system 31 in the area B, and the data of the small steel uploaded by the lower system 31 in the area C are combined into a relationship table for recording the data of the small steel, the data of the small steel uploaded by the lower system 31 in the area a, the data of the small steel uploaded by the lower system 31 in the area B, and the data of the small steel uploaded by the lower system 31 in the area C to be associated with each other.
The lower-level clustering data includes a current identifier, and the clustering data is merged according to the merging relation table, referring to fig. 2, including:
s22: judging whether the current identification exists in the associated information recorded by the combination relation table;
in this embodiment, it is described by taking an example that the lower-level cluster data is a small rigid data, and the lower-level cluster data includes a current identifier, for example, the current identifier included in the cluster data of the lower-level system 31 in the a region is a small rigid data. Similarly, the cluster data of the B regional subordinate system 31 includes the current identifier of B-small rigid data, and the cluster data of the C regional subordinate system 31 includes the current identifier of C-small rigid data. The unified identification of the data merge group is small steel data, and the merge relation table is used for recording that the small steel data, the A-small steel data, the B-small steel data and the C-small steel data are correlated with each other.
Judging whether the current identification of A-small rigid data exists in the associated information recorded by the combination relation table;
and two cases are derived, referring to fig. 2, including:
s221: and if so, merging the lower-level clustering data into a merging group corresponding to the unified identification included in the associated information to which the current identification belongs.
If the current identifier of a-small rigid data exists in the association information recorded in the merge relationship table, which represents that the system 31 in the lower level of the a region has uploaded small rigid data once, the merge relationship table associates the current identifier of a-small rigid data, so that the current identifier of a-small rigid data exists in the association information of the merge relationship table. At this time, the minor data uploaded by the lower system 31 in the a region is merged into a merged group corresponding to the same identifier included in the related information to which the current identifier a-minor data belongs. The same identifier included in the associated information of the current identifier A-little steel data is the little steel data. The combination group corresponding to the small steel data is a small steel data combination group.
S222: if not, comparing the lower-level clustering data with the data in each merging group, and judging whether data matched with the lower-level clustering data exist or not;
if the current identifier of a-small rigid data does not exist in the association information recorded in the merge relationship table, it represents that the system 31 in the lower level of the a region uploads the small rigid data for the first time, and the current identifier of the a-small rigid data is not associated before the merge relationship table.
The data in the small rigid data uploaded by the lower system 31 in the area a and the data in each merged group are compared to determine whether there is data matching with the data in the small rigid data uploaded by the lower system 31 in the area a. The matched data is, for example, the small rigidity data uploaded by the B region lower system 31 in the small rigidity data merge group, the small rigidity data uploaded by the C region lower system 31, and the like.
The data alignment may be calculated by a clustering engine.
And two cases are derived, referring to fig. 2, including:
s2221: and if the matched data exists, merging the lower-level clustering data into a merging group where the matched data exists.
If there is data matching the small steel data uploaded by the lower system 31 in area a, the small steel data is merged into a group. The data of the small steel uploaded by the system 31 in the lower level of the a territory is merged into the merged group where the matched data is located, namely the merged group of the data of the small steel.
S2222: if no matched data exists, a merging group is created, the lower-level clustering data is merged into the newly created merging group, a unified identification is newly distributed to the merging group, an associated message is newly added in the merging relation table, and the newly added associated relation comprises the newly distributed unified identification.
If there is no data matching the small rigid data uploaded by the lower system 31 in the a region, that is, the upper system 32 never receives any small rigid data uploaded by the lower system 31, and a small rigid data merge group is not established. A merge group is created, the small rigid data uploaded by the system 31 in the lower level of the a area is merged into the newly created merge group, and a uniform identifier, such as small rigid data, is newly allocated to the merge group. And newly adding a piece of association information in the combination relation table, wherein the small steel data and the A-small steel data are associated with each other.
S13: and determining the video data in the same merge group as a group of upper-level cluster data.
Taking the small steel data merge group as an example, the video data in the small steel data merge group is determined as a group of upper-level cluster data. Cluster data for representing the thumbnail video data within the corresponding cluster range of the upper level system 32.
In this embodiment, the lower system 31 firstly clusters the video data in the corresponding clustering range once, the corresponding clustering range of the lower system 31 can be a small region range such as county and county, and the lower system 31 clusters the video data in the small region, so that the clustering accuracy is high. And receiving the lower-level clustering data reported by each lower-level system 31, merging the lower-level clustering data, merging the matched lower-level clustering data of different lower-level systems 31 into the same merging group, and determining the video data in the same merging group as a group of upper-level clustering data. Because each group of superior clustering data is obtained by combining the subordinate clustering data with high clustering precision, the clustering precision of each group of superior clustering data is also higher, namely the data clustering accuracy in a large-scale and massive data environment is improved.
The video data processing method in some embodiments, further comprising: establishing a cascade relationship with the subordinate system 31;
after determining the lower-level clustering data reported by the lower-level system 31 as the upper-level clustering data, the upper-level clustering data is synchronized to the lower-level system 31 from which the lower-level clustering data comes based on the cascading service.
The cascade refers to the mapping relation among a plurality of objects in computer science, and establishes the cascade relation among data to improve the management efficiency. Cascading is an important concept in associative mapping, which refers to whether a passive side performs the same operation synchronously when an active side object performs the operation. In this embodiment, the active side may be the upper system 32, and the passive side may be the lower system 31.
By using the cascade relation, the lower system 31 can obtain the upper cluster data of the upper system 32 and store or use the data.
Further, if the merge group has the uniform identifier, after merging the clustering data, the method further includes:
determining a unified identification of a merging group into which lower-level clustering data are merged;
the unified identifier is transmitted to the lower system 31 from which the lower clustered data is received, so that the lower system 31 identifies the lower clustered data with the unified identifier in the lower system 31.
The lower system 31 and the upper system 32 in the cascade mode unify the identifiers of the lower clustering data and the upper clustering data.
For example, the data of the small message uploaded by the system 31 in the lower level of the a area is merged into the data merged group, and the unified identifier is the data of the small message. The uniform identification of the small rigid data is sent to the subordinate system 31 of the area A, so that the subordinate system 31 of the area A uses the uniform identification of the small rigid data to identify subordinate clustered data in the area A, and therefore the uniform identification of the subordinate clustered data and the superior clustered data is achieved.
The video data processing method in some embodiments, wherein the current identifier is:
a uniform identifier corresponding to the lower-level cluster data, the uniform identifier being obtained by the lower-level system 31 from the upper-level system 32 and used for identifying the lower-level cluster data; alternatively, the first and second electrodes may be,
the lower clustering data of different lower systems 31 have different lower identifications, and the associated information further includes lower identifications, and each uniform identification is associated with one or more lower identifications.
The lower system 31 performs lower identification on the lower clustered data when the lower system 31 does not acquire the uniform identification from the upper system 32, such as the lower system 31 of the a region identifying the data as a-little data. The a-small rigid data is a lower identifier corresponding to the lower clustering data of the lower system 31 in the a region. Similarly, the lower cluster data of the lower system 31 in the B area corresponds to the lower identifier of B-bar data.
And in the merging relation table, the small steel data is used as a unified identification to establish association information with a plurality of lower identifications, such as A-small steel data, B-small steel data and C-small steel data.
The video data processing method in some embodiments, further comprising:
the upper level cluster data is stored or applied at the upper level system 32.
The superior clustering data is stored for convenient later use.
The upper level cluster data is applied to various data services.
Fig. 3 is a block diagram of a video data processing system according to an embodiment of the present application, and referring to fig. 3, a video data processing system includes:
each lower system 31 is used for clustering the video data in the corresponding clustering range to obtain corresponding lower clustering data;
the upper system 32 is used for receiving the lower clustering data and merging the lower clustering data, so that the matched lower clustering data of different lower systems 31 are merged into the same merging group; and determining the video data in the same merge group as a group of upper-level cluster data.
The lower system 31 may be a data processing system established in a small geographic area such as county or county, and the corresponding clustering area of the lower system 31 may be a small geographic area such as county or county.
The upper level system 32 may be a data processing system in a large territorial scope such as province and city, and the corresponding clustering scope of the upper level system 32 may be the large territorial scope such as province and city.
The video data processing system in some embodiments, further comprising:
and the cascade service system 33 is configured to receive the lower-level cluster data and send the lower-level cluster data to the upper-level system 32.
The cascade refers to the mapping relation among a plurality of objects in computer science, and establishes the cascade relation among data to improve the management efficiency. Cascading is an important concept in associative mapping, which refers to whether a passive side performs the same operation synchronously when an active side object performs the operation. In this embodiment, the active side may be a lower system 31, the passive side may be an upper system 32, and the lower system 31 sends the lower cluster data to the upper system 32 through the cascade service system 33.
In other embodiments, the active side may also be the upper system 32, and the passive side may also be the lower system 31, so that the lower system 31 can obtain the upper clustering data of the upper system 32 through the cascading service system 33.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that, in the description of the present application, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present application, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A method of processing video data, comprising:
receiving lower-level clustering data reported by each lower-level system, wherein the lower-level clustering data are obtained by clustering video data in a corresponding clustering range by each lower-level system, and the number of the lower-level systems is multiple;
merging the lower-level clustering data to merge the matched lower-level clustering data of different lower-level systems into the same merging group;
and determining the video data in the same merge group as a group of upper-level cluster data.
2. The method of claim 1, wherein prior to the merging the clustered data, the method further comprises:
and acquiring a merging relation table stored in a superior system to merge the clustering data according to the merging relation table, wherein the merging relation table is used for recording associated information, the associated information comprises uniform identification, and different merging groups have different uniform identification.
3. The method according to claim 2, wherein the lower-level cluster data includes a current identifier, and the merging the cluster data according to the merge relationship table includes:
judging whether the current identification exists in the associated information recorded by the combination relation table;
and if so, merging the lower-level clustering data into a merging group corresponding to the unified identification included in the associated information to which the current identification belongs.
4. The method of claim 3, further comprising:
if not, comparing the lower-level clustering data with the data in each merging group, and judging whether data matched with the lower-level clustering data exist or not;
and if the matched data exists, merging the lower-level clustering data into a merging group where the matched data is located.
5. The method of claim 4, further comprising:
if no matched data exists, a merging group is newly established, the lower-level clustering data is merged into the newly established merging group, a unified identification is newly distributed to the merging group, an associated message is newly added in the merging relation table, and the newly added associated relation comprises the newly distributed unified identification.
6. The method according to any one of claims 1 to 5, wherein if the merged group has a uniform identifier, after the merging the clustered data, the method further comprises:
determining a unified identifier of a merging group into which the lower-level clustering data is merged;
and sending the uniform identifier to a subordinate system from which the subordinate clustered data come, so that the subordinate system uses the uniform identifier to identify the subordinate clustered data in the subordinate system.
7. The method of claim 6, wherein the current identity is:
a uniform identifier corresponding to the subordinate clustered data, wherein the uniform identifier is obtained by the subordinate system from the superior system before and is used for identifying the subordinate clustered data; alternatively, the first and second electrodes may be,
the lower-level clustering data of different lower-level systems have different lower-level identifications, the associated information further comprises lower-level identifications, and each uniform identification is associated with one or more lower-level identifications.
8. The method according to any one of claims 1-5, further comprising:
and storing or applying the upper-level clustering data in an upper-level system.
9. A video data processing system, comprising:
each lower system is used for clustering the video data in the corresponding clustering range to obtain corresponding lower clustering data;
the upper-level system is used for receiving the lower-level clustering data and merging the lower-level clustering data, so that the matched lower-level clustering data of different lower-level systems are merged into the same merging group; and determining the video data in the same merge group as a group of upper-level cluster data.
10. The video data processing system of claim 9, further comprising:
and the cascade service system is used for receiving the lower-level clustering data and sending the lower-level clustering data to the upper-level system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911022529.2A CN110781815B (en) | 2019-10-25 | 2019-10-25 | Video data processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911022529.2A CN110781815B (en) | 2019-10-25 | 2019-10-25 | Video data processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110781815A true CN110781815A (en) | 2020-02-11 |
| CN110781815B CN110781815B (en) | 2022-09-27 |
Family
ID=69387745
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911022529.2A Active CN110781815B (en) | 2019-10-25 | 2019-10-25 | Video data processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110781815B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113987089A (en) * | 2021-12-28 | 2022-01-28 | 北京力控元通科技有限公司 | System cascading method, data processing method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103838863A (en) * | 2014-03-14 | 2014-06-04 | 内蒙古科技大学 | Big-data clustering algorithm based on cloud computing platform |
| CN106845536A (en) * | 2017-01-09 | 2017-06-13 | 西北工业大学 | A kind of parallel clustering method based on image scaling |
| CN108717444A (en) * | 2018-05-17 | 2018-10-30 | 安阳工学院 | A kind of big data clustering method and device based on distributed frame |
| US20190005107A1 (en) * | 2017-06-28 | 2019-01-03 | International Business Machines Corporation | Clustering database data |
| CN110046187A (en) * | 2018-12-25 | 2019-07-23 | 阿里巴巴集团控股有限公司 | Data processing system, method and device |
-
2019
- 2019-10-25 CN CN201911022529.2A patent/CN110781815B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103838863A (en) * | 2014-03-14 | 2014-06-04 | 内蒙古科技大学 | Big-data clustering algorithm based on cloud computing platform |
| CN106845536A (en) * | 2017-01-09 | 2017-06-13 | 西北工业大学 | A kind of parallel clustering method based on image scaling |
| US20190005107A1 (en) * | 2017-06-28 | 2019-01-03 | International Business Machines Corporation | Clustering database data |
| CN108717444A (en) * | 2018-05-17 | 2018-10-30 | 安阳工学院 | A kind of big data clustering method and device based on distributed frame |
| CN110046187A (en) * | 2018-12-25 | 2019-07-23 | 阿里巴巴集团控股有限公司 | Data processing system, method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113987089A (en) * | 2021-12-28 | 2022-01-28 | 北京力控元通科技有限公司 | System cascading method, data processing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110781815B (en) | 2022-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104156937B (en) | shadow detection method and device | |
| US11922482B2 (en) | Self-checkout system, purchased product management method, and purchased product management program | |
| TWI740537B (en) | Information processing method, device and storage medium thereof | |
| WO2020259099A1 (en) | Information processing method and device, and storage medium | |
| Iguernaissi et al. | People tracking in multi-camera systems: a review | |
| JP2004361987A (en) | Image retrieval system, image classification system, image retrieval program, image classification program, image retrieval method, and image classification method | |
| Solanki et al. | Automatic Identification of Temples in Digital Images through Scale Invariant Feature Transform | |
| CN107615298A (en) | Face identification method and system | |
| JP2015106300A (en) | Image search device, control method for image search device, and program | |
| CN112818149A (en) | Face clustering method and device based on space-time trajectory data and storage medium | |
| CN110781815B (en) | Video data processing method and system | |
| Xu et al. | Dual-channel CNN for efficient abnormal behavior identification through crowd feature engineering | |
| CN110413839A (en) | A kind of label data sharing method, device and the equipment of image capture device | |
| Bartoli et al. | Museumvisitors: a dataset for pedestrian and group detection, gaze estimation and behavior understanding | |
| WO2021104388A1 (en) | System and method for interactive perception and content presentation | |
| Zaman et al. | A robust deep networks based multi-object multi-camera tracking system for city scale traffic | |
| JP2023153148A (en) | Self-register system, purchased commodity management method and purchased commodity management program | |
| CN116071569A (en) | Image selection method, computer equipment and storage device | |
| CN115661624A (en) | Digital method and device for goods shelf and electronic equipment | |
| Dhamecha et al. | CrowdFaceDB: Database and benchmarking for face verification in crowd | |
| CN111382650A (en) | Commodity shopping processing system, method and device and electronic equipment | |
| Zimoch et al. | Human flow recognition using deep networks and vision methods | |
| Jadhav et al. | An Instance Segmentation Model to Categorize Clothes from Wild Fashion Images | |
| Ranganarayana et al. | A Study on Approaches For Identifying Humans In Low Resolution Videos | |
| JP2019083058A (en) | Image processor and image processing program |
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 |