CN108200390A - Video structure analyzing method and device - Google Patents
Video structure analyzing method and device Download PDFInfo
- Publication number
- CN108200390A CN108200390A CN201711465772.2A CN201711465772A CN108200390A CN 108200390 A CN108200390 A CN 108200390A CN 201711465772 A CN201711465772 A CN 201711465772A CN 108200390 A CN108200390 A CN 108200390A
- Authority
- CN
- China
- Prior art keywords
- video
- scene
- frame
- identification
- image
- 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application discloses a kind of video structure analyzing method and devices.Method passes through：Receive the video analyzed；Image identification is carried out to the need identification object in the video frame by frame according to sequential；Each analysis result that need to identify object is obtained, and as each structured message that need to identify object；Output need to each identify the structured message of object.Having reached can help machine to understand video content, so as to which machine be allowed to realize some things that manual operation was needed to complete originally；By automation, the technical issues of to substitute hand labor.
Description
Technical field
This application involves video image identification field, in particular to a kind of video structure analyzing method and device.
Background technology
U.S. Department of Defense research shows that, in a non intelligent video monitoring system, staff monitoring two
Platform monitor forgets 45% content after ten minutes, can forget 95% content after twenty minutes ", this is nearly 2 years each videos
Analysis manufacturer has often used " words art " when promoting Video Analysis Technology and product.Therefore, video monitoring system needs intelligence, is
System is needed with can be as people with the ability thought independently, and overcomes the shortcomings of some artificial monitoring behaviors.It is well known that
The development experience of Video Supervision Technique cctv surveillance epoch, DVR epoch and network monitoring epoch.
In the cctv surveillance epoch, the vision signal of front end is selected and cut by the control handoff functionality realization of matrix
It changes on specified monitor, operator on duty needs to stare at monitor with breathless interest with the doubtful situations that try to find out.Due to camera shooting
Machine and monitor are not one-to-one proportional arrangement, therefore the information for missing some video cameras is inevitable, the DVR epoch, video
Monitoring system realizes certain digitlization, using Video coding and hard disk storage devices, can carry out large capacity and record for a long time
Picture, still, the functioning side of DVR are focused in " video recording ", therefore, the main function of DVR be typically post-survey playback use and cannot
It prevents trouble before it happens, part DVR equipment realizes " the primary intelligence " of VMD (video movement Detection Techniques), but practical application is imitated
Fruit is simultaneously bad, is not really video analysis.In conclusion closed-circuit TV monitoring system, digital video monitor system have following weakness：
Video camera is typically according to " many-one " proportional arrangement with monitor, can not monitor all channels；
For simulated television wall, the attention of people cannot centralized watch and ahead of time discovery suspicious actions forever；
DVR/NVR is typically video recording effect, and post-survey when needed is used；
The search function of DVR/NVR is single, without intelligent retrieval function；
Independent " understanding " video information of computer system can be allowed, so as to instead of operator on duty, realize to video content
Automatic judgement is the key point of intelligent Video Surveillance Technology；But before this, machine is understood almost without method in video
Hold.
For in the relevant technologies and its problem of can not understanding video content, currently no effective solution has been proposed.
Invention content
The main purpose of the application is to provide a kind of video structure analyzing method, to solve present in the relevant technologies
Problem.
To achieve these goals, according to the one side of the application, a kind of video structure analyzing method is provided.
Included according to the video structure analyzing method method of the application：
Receive the video analyzed；
Image identification is carried out to the need identification object in the video frame by frame according to sequential；
Each analysis result that need to identify object is obtained, and as each structured message that need to identify object；
Output need to each identify the structured message of object.
Further, video structure analyzing method as the aforementioned, it is described according to sequential frame by frame to the need in the video
Identify that object carries out image identification, including：
According to sequential frame by frame in the video personage, three classifications of object and scene image information carry out image knowledge
Not；
Identification obtains the image information of all specific personages, object and scene occurred in every frame image of the video.
Further, video structure analyzing method as the aforementioned, it is described to obtain each analysis result that identify object,
Including：
According to the obtained image information of all specific personages, object and scene of identification, obtain each specific personage,
The title of object and scene, time of occurrence, duration and total duration.
Further, video structure analyzing method as the aforementioned, each specific personage, object and the scene of obtaining
Title, including：
The image information of all specific personages, object and scene is scanned in server or internet
Match, obtain corresponding match information；
And using the match information as the title of corresponding specific personage, object and scene.
Further, video structure analyzing method as the aforementioned obtains each analysis knot that need to identify object described
After fruit, further include：
The name box of each specific personage, object and scene are shown in the video on corresponding image-region.
To achieve these goals, according to the another aspect of the application, a kind of video structure analyzing device is provided.
Included according to the video structure analyzing device of the application：
Receiving unit, for receiving the video analyzed；
Image identification unit, for carrying out image identification to the need identification object in the video frame by frame according to sequential；
Structured message obtaining unit for obtaining each analysis result that need to identify object, and is used as each need
Identify the structured message of object；
Structured message output unit, for exporting the structured message that need to each identify object.
Further, video structure analyzing device as the aforementioned, described image recognition unit, including：
Classification and Identification module, for according to sequential frame by frame in the video personage, object and scene three classifications
Image information carries out image identification；
Image information obtain module, for identify obtain all specific personages occurred in every frame image of the video,
The image information of object and scene.
Further, video structure analyzing device as the aforementioned, the structured message obtaining unit, including：Structure
Change information acquisition module；
The structured message obtains module, for all specific personages, object and the scene obtained according to identification
Image information, obtain title, time of occurrence, duration and the total duration of each specific personage, object and scene.
Further, video structure analyzing device as the aforementioned, the structured message obtain module, including：
Search for submodule, for by the image information of all specific personages, object and scene in server or interconnection
It scans for matching in net, obtains corresponding match information；
Name-matches submodule is used for and using the match information as corresponding specific personage, object and scene
Title.
Further, video structure analyzing device as the aforementioned, further includes：Message box shows unit；
Described information frame shows unit, is regarded for showing the name box of each specific personage, object and scene described
In frequency on corresponding image-region.
In the embodiment of the present application, by the way of video data structure, by receiving the video analyzed；
Image identification is carried out to the need identification object in the video frame by frame according to sequential；Obtain each analysis knot that need to identify object
Fruit, and as each structured message that need to identify object；Output need to each identify the structured message of object.Reach
Machine can be helped to understand video content, so as to which machine be allowed to realize some things that manual operation was needed to complete originally；By certainly
Dynamicization, the technical issues of to substitute hand labor.
Description of the drawings
The attached drawing for forming the part of the application is used for providing further understanding of the present application so that the application's is other
Feature, objects and advantages become more apparent upon.The illustrative examples attached drawing and its explanation of the application is for explaining the application, not
Form the improper restriction to the application.In the accompanying drawings：
Fig. 1 is a kind of method flow schematic diagram of embodiment of video structure analyzing method of the present invention；
Fig. 2 is a kind of flow diagram of embodiment of step S2 in method as shown in Figure 1；
Fig. 3 is a kind of module connection diagram of embodiment of video structure analyzing device of the present invention；
Fig. 4 is a kind of module connection of embodiment of image identification unit in video structure analyzing device shown in Fig. 3
Schematic diagram；And
Fig. 5 is the module connection diagram of another video structure analyzing device embodiment of the present invention.
Specific embodiment
In order to which those skilled in the art is made to more fully understand application scheme, below in conjunction in the embodiment of the present application
The technical solution in the embodiment of the present application is clearly and completely described in attached drawing, it is clear that described embodiment is only
The embodiment of the application part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's all other embodiments obtained without making creative work should all belong to the model of the application protection
It encloses.
It should be noted that term " first " in the description and claims of this application and above-mentioned attached drawing, "
Two " etc. be the object for distinguishing similar, and specific sequence or precedence are described without being used for.It should be appreciated that it uses in this way
Data can be interchanged in the appropriate case, so as to embodiments herein described herein.In addition, term " comprising " and " tool
Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing series of steps or unit
Process, method, system, product or equipment are not necessarily limited to those steps or unit clearly listed, but may include without clear
It is listing to Chu or for the intrinsic other steps of these processes, method, product or equipment or unit.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
As shown in Figure 1, the present invention provides a kind of video structure analyzing methods.
Included according to the video structure analyzing method method of the application：
S1. the video analyzed is received；Specifically, local user can will be needed by wired or wireless network
The video analyzed is uploaded in the platform or server of the video analysis ability with the present invention；
S2. image identification is carried out to the need identification object in the video frame by frame according to sequential；Specifically, the figure identified
As analysis result is also arranged according to sequential；
S3. each analysis result that need to identify object is obtained, and as each structured message that need to identify object；
S4. the structured message of object need to each be identified by exporting.
Having been reached by the above method can help machine to understand video content, so as to which machine be allowed to realize some original needs
The thing that manual operation is completed；By automation, the technical issues of to substitute hand labor.
As shown in Fig. 2, in some embodiments, video structure analyzing method as the aforementioned, in the step S2 according to
Sequential carries out image identification to the need identification object in the video frame by frame, including：
S21. according to sequential frame by frame in the video personage, the image information of three classifications of object and scene carry out figure
As identification；
S22. identification obtains the image letter of all specific personages, object and the scene that occur in every frame image of the video
Breath.
Specifically, the personage in the video refers to all recognitions of face appeared in the video and engineering
The personage that the mode of habit identifies, the object can include the consumer goods (clothes, packet and shoes etc.), and the scene can be
Building (building, sculpture), street and sight spot etc.；The recognition methods to object and scene can be the side such as machine learning
Formula.
Further, video structure analyzing method as the aforementioned obtains in the step S3 each to identify object
Analysis result, including：
According to the obtained image information of all specific personages, object and scene of identification, obtain each specific personage,
The title of object and scene, time of occurrence, duration and total duration.
Then using each specific personage, the title of object and scene, time of occurrence, duration and total duration as
Each structured message that need to identify object.
Specifically the time of occurrence is specially：In adjacent two field pictures, former frame does not occur and goes out in the next frame
In the case of existing, to there is the time of the place frame of a certain specific personage, object and scene as the specific personage, object
The time of occurrence of body and scene when a certain specific personage, object and scene are not appeared in the video, obtains
The corresponding end time, and the corresponding duration is obtained according to the time of occurrence and end time；The duration with
The time of occurrence corresponds；And can occur one or more groups of time of occurrence in same video file；And by institute
The addition of all duration for stating a certain specific personage, object and scene in video can obtain the total duration.
Further, video structure analyzing method as the aforementioned, each specific personage, object and the scene of obtaining
Title, including：
The image information of all specific personages, object and scene is scanned in server or internet
Match, obtain corresponding match information；
And using the match information as the title of corresponding specific personage, object and scene.
Specifically, the title of specific personage, object and scene matched herein is in online or matching service
Personage, object and the scene of corresponding information can be searched in device；It is corresponding when that can not be matched in online or match server
When the personage of information, object and scene, then corresponding name information is not obtained.
Further, video structure analyzing method as the aforementioned obtains each analysis knot that need to identify object described
After fruit, further include：
The name box of each specific personage, object and scene are shown in the video on corresponding image-region.
It should be noted that step shown in the flowchart of the accompanying drawings can be in such as a group of computer-executable instructions
It is performed in computer system, although also, show logical order in flow charts, it in some cases, can be with not
The sequence being same as herein performs shown or described step.
According to embodiments of the present invention, a kind of device for being used to implement above-mentioned video structure analyzing method is additionally provided, such as
Shown in Fig. 3, which includes：
Included according to the video structure analyzing device of the application：
Receiving unit 1, for receiving the video analyzed；
Image identification unit 2, for carrying out image identification to the need identification object in the video frame by frame according to sequential；
Structured message obtaining unit 3 for obtaining each analysis result that need to identify object, and is used as each need
Identify the structured message of object；
Structured message output unit 4, for exporting the structured message that need to each identify object.
As shown in figure 4, in some embodiments, video structure analyzing device as the aforementioned, described image recognition unit
2, including：
Classification and Identification module 21, for according to sequential frame by frame in the video personage, three classifications of object and scene
Image information carry out image identification；
Image information obtains module 22, and all specific people occurred in every frame image of the video are obtained for identifying
The image information of object, object and scene.
Further, video structure analyzing device as the aforementioned, the structured message obtaining unit 3, including：Structure
Change information acquisition module；
The structured message obtains module, for all specific personages, object and the scene obtained according to identification
Image information, obtain title, time of occurrence, duration and the total duration of each specific personage, object and scene.
Further, video structure analyzing device as the aforementioned, the structured message obtain module, including：
Search for submodule, for by the image information of all specific personages, object and scene in server or interconnection
It scans for matching in net, obtains corresponding match information；
Name-matches submodule is used for and using the match information as corresponding specific personage, object and scene
Title.
As shown in figure 5, in some embodiments, video structure analyzing device as the aforementioned further includes：Message box shows list
Member 5；
Described information frame shows unit 5, is regarded for showing the name box of each specific personage, object and scene described
In frequency on corresponding image-region.
Obviously, those skilled in the art should be understood that each module of the above-mentioned present invention or each step can be with general
Computing device realize that they can concentrate on single computing device or be distributed in multiple computing devices and be formed
Network on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
In the storage device by computing device come perform either they are fabricated to respectively each integrated circuit modules or by they
In multiple modules or step be fabricated to single integrated circuit module to realize.In this way, the present invention is not limited to any specific
Hardware and software combines.
The foregoing is merely the preferred embodiments of the application, are not limited to the application, for the skill of this field
For art personnel, the application can have various modifications and variations.It is all within spirit herein and principle, made any repair
Change, equivalent replacement, improvement etc., should be included within the protection domain of the application.
Claims (10)
- A kind of 1. video structure analyzing method, which is characterized in that including：Receive the video analyzed；Image identification is carried out to the need identification object in the video frame by frame according to sequential；Each analysis result that need to identify object is obtained, and as each structured message that need to identify object；Output need to each identify the structured message of object.
- 2. video structure analyzing method according to claim 1, which is characterized in that it is described according to sequential frame by frame to described Need identification object in video carries out image identification, including：According to sequential frame by frame in the video personage, three classifications of object and scene image information carry out image identification；Identification obtains the image information of all specific personages, object and scene occurred in every frame image of the video.
- 3. video structure analyzing method according to claim 2, which is characterized in that described to obtain each to identify object Analysis result, including：According to the image information of all specific personages, object and scene that identification obtains, each specific personage, object are obtained And title, time of occurrence, duration and the total duration of scene.
- 4. video structure analyzing method according to claim 2, which is characterized in that it is described obtain each specific personage, The title of object and scene, including：The image information of all specific personages, object and scene is scanned for matching in server or internet, is obtained Obtain corresponding match information；And using the match information as the title of corresponding specific personage, object and scene.
- 5. video structure analyzing method according to claim 4, which is characterized in that obtain each need to identify pair described After the analysis result of elephant, further include：The name box of each specific personage, object and scene are shown in the video on corresponding image-region.
- 6. a kind of video structure analyzing device, which is characterized in that including：Receiving unit, for receiving the video analyzed；Image identification unit, for carrying out image identification to the need identification object in the video frame by frame according to sequential；Structured message obtaining unit for obtaining each analysis result that need to identify object, and each needs to identify as described The structured message of object；Structured message output unit, for exporting the structured message that need to each identify object.
- 7. video structure analyzing device according to claim 6, which is characterized in that described image recognition unit, including：Classification and Identification module, for according to sequential frame by frame in the video personage, the image of three classifications of object and scene Information carries out image identification；Image information obtains module, and all specific personages occurred in every frame image of the video, object are obtained for identifying And the image information of scene.
- 8. video structure analyzing device according to claim 7, which is characterized in that the structured message obtains single Member, including：Structured message obtains module；The structured message obtains module, for the figure of all specific personages, object and scene obtained according to identification As information, title, time of occurrence, duration and the total duration of each specific personage, object and scene are obtained.
- 9. video structure analyzing device according to claim 8, which is characterized in that the structured message obtains mould Block, including：Search for submodule, for by the image information of all specific personages, object and scene in server or internet It scans for matching, obtains corresponding match information；Name-matches submodule, is used for and the title using the match information as corresponding specific personage, object and scene.
- 10. video structure analyzing device according to claim 9, which is characterized in that further include：Message box shows unit；Described information frame shows unit, for showing the name box of each specific personage, object and scene in the video On corresponding image-region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711465772.2A CN108200390A (en) | 2017-12-28 | 2017-12-28 | Video structure analyzing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711465772.2A CN108200390A (en) | 2017-12-28 | 2017-12-28 | Video structure analyzing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108200390A true CN108200390A (en) | 2018-06-22 |
Family
ID=62585982
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711465772.2A Pending CN108200390A (en) | 2017-12-28 | 2017-12-28 | Video structure analyzing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108200390A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111314652A (en) * | 2018-12-11 | 2020-06-19 | 顺丰科技有限公司 | Video structured analysis processing method, device, equipment and storage medium thereof |
| CN112565717A (en) * | 2021-02-18 | 2021-03-26 | 深圳市安软科技股份有限公司 | Video structuring method, related device, system and storage medium |
| CN114501165A (en) * | 2020-10-23 | 2022-05-13 | 国家广播电视总局广播电视科学研究院 | Video structured representation method and device and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120309463A1 (en) * | 2011-06-03 | 2012-12-06 | Lee Joowoo | Mobile terminal and method of managing information in the same |
| CN103778237A (en) * | 2014-01-27 | 2014-05-07 | 北京邮电大学 | Video abstraction generation method based on space-time recombination of active events |
| CN103780973A (en) * | 2012-10-17 | 2014-05-07 | 三星电子（中国）研发中心 | Video label adding method and video label adding device |
| CN105279480A (en) * | 2014-07-18 | 2016-01-27 | 顶级公司 | Method of video analysis |
| CN106708890A (en) * | 2015-11-17 | 2017-05-24 | 创意引晴股份有限公司 | Intelligent high-fault-tolerance video recognition system based on multi-mode fusion and recognition method thereof |
-
2017
- 2017-12-28 CN CN201711465772.2A patent/CN108200390A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120309463A1 (en) * | 2011-06-03 | 2012-12-06 | Lee Joowoo | Mobile terminal and method of managing information in the same |
| CN103780973A (en) * | 2012-10-17 | 2014-05-07 | 三星电子（中国）研发中心 | Video label adding method and video label adding device |
| CN103778237A (en) * | 2014-01-27 | 2014-05-07 | 北京邮电大学 | Video abstraction generation method based on space-time recombination of active events |
| CN105279480A (en) * | 2014-07-18 | 2016-01-27 | 顶级公司 | Method of video analysis |
| CN106708890A (en) * | 2015-11-17 | 2017-05-24 | 创意引晴股份有限公司 | Intelligent high-fault-tolerance video recognition system based on multi-mode fusion and recognition method thereof |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111314652A (en) * | 2018-12-11 | 2020-06-19 | 顺丰科技有限公司 | Video structured analysis processing method, device, equipment and storage medium thereof |
| CN111314652B (en) * | 2018-12-11 | 2022-03-29 | 顺丰科技有限公司 | Video structured analysis processing method, device, equipment and storage medium thereof |
| CN114501165A (en) * | 2020-10-23 | 2022-05-13 | 国家广播电视总局广播电视科学研究院 | Video structured representation method and device and electronic equipment |
| CN112565717A (en) * | 2021-02-18 | 2021-03-26 | 深圳市安软科技股份有限公司 | Video structuring method, related device, system and storage medium |
| CN112565717B (en) * | 2021-02-18 | 2021-05-25 | 深圳市安软科技股份有限公司 | Video structuring method, related device, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9729834B2 (en) | Identifying spatial locations of events within video image data | |
| US9251425B2 (en) | Object retrieval in video data using complementary detectors | |
| US8165348B2 (en) | Detecting objects crossing a virtual boundary line | |
| US9883193B2 (en) | Coding scheme for identifying spatial locations of events within video image data | |
| US20230093631A1 (en) | Video search device and network surveillance camera system including same | |
| US20110302130A1 (en) | Intelligent video information retrieval apparatus and method capable of multi-dimensional video indexing and retrieval | |
| CN103795976A (en) | Full space-time three-dimensional visualization method | |
| CN105279480A (en) | Method of video analysis | |
| CN110796098A (en) | Method, device, equipment and storage medium for training and auditing content auditing model | |
| CN108200390A (en) | Video structure analyzing method and device | |
| CN105450978A (en) | Method and device for achieving structural description in video monitoring system | |
| KR101990789B1 (en) | Method and Apparatus for Searching Object of Interest by Selection of Object | |
| KR20160093253A (en) | Video based abnormal flow detection method and system | |
| Li et al. | Evaluation of an ivs system for abandoned object detection on pets 2006 datasets | |
| KR101547255B1 (en) | Object-based Searching Method for Intelligent Surveillance System | |
| CN110300290B (en) | Teaching monitoring management method, device and system | |
| KR20190051924A (en) | Method and Apparatus for Searching Object of Interest by Selection of Object | |
| KR20210108691A (en) | apparatus and method for multi-channel image back-up based on event, and network surveillance camera system including the same | |
| CN109120896B (en) | Security video monitoring guard system | |
| US20220286642A1 (en) | Event-oriented multi-channel video backup apparatus and method, and network surveillance camera system including the same | |
| KR20140052744A (en) | Method and apparatus for searching event occurred in image | |
| CN113779309A (en) | Video screening method based on face recognition | |
| KR20130104024A (en) | Apparatus for searching image data | |
| Park et al. | Videos analytic retrieval system for CCTV surveillance | |
| Shubhangi et al. | Deep Neural Network Based Anomaly Detection For Smart Surveillance System |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20180622 Assignee: Apple R&D (Beijing) Co.,Ltd. Assignor: BEIJING MOSHANGHUA TECHNOLOGY Co.,Ltd. Contract record no.: 2019990000054 Denomination of invention: Video structural analysis method and device License type: Exclusive License Record date: 20190211 |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180622 |