CN107707857A - A kind of method for recorded video of classifying - Google Patents
A kind of method for recorded video of classifying Download PDFInfo
- Publication number
- CN107707857A CN107707857A CN201710980630.3A CN201710980630A CN107707857A CN 107707857 A CN107707857 A CN 107707857A CN 201710980630 A CN201710980630 A CN 201710980630A CN 107707857 A CN107707857 A CN 107707857A
- Authority
- CN
- China
- Prior art keywords
- video data
- video
- recorded
- memory
- indicatrix
- 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
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
-
- 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
-
- 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
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)
- Television Signal Processing For Recording (AREA)
Abstract
The invention provides a kind of method for recorded video of classifying, it is related to video record field.This method includes：S1, record command is received, creates a recorded file in memory, and gather video data, the video data of collection is cached into internal memory random access memory；Wherein, video data is the raw image data captured by camera sensor；S2, when the video data in the random access memory reaches a preset value, continue to gather video data, wherein, the residual memory space of the memory is detected, when the residual memory space of the memory reaches preset value, travels through the video data in the random access memory, video data in the random access memory is classified, coding is compressed to the video data classified；S3, the video data classified is write by recorded file according to preparatory condition respectively.
Description
Technical field
The present invention relates to video record field, more particularly to a kind of method for recorded video of classifying.
Background technology
With advancing by leaps and bounds using multimedia as the IT industry of representative, safety of the people to live and work environment
Property require also improving constantly, monitor and control facility is increasingly appearing in various public places.At present, video monitoring system has been
It has been related to all trades and professions of social life, such as traffic intersection, supermarket, bank, station and residential area etc., at the same time,
Many monitoring devices are also provided in guard's work in various large-scale activity places and important defendance region, such as Olympic Games meeting-place
Ground, People's Square, Expo Site etc..
At the same time, due to the appearance of magnanimity monitor video data, the traditional video surveillance system manually supervised is fully relied on
System has been unable to meet demand, and people need more intelligent, automation, the video monitoring system of autonomy-oriented, therefore intelligent video
Monitoring system becomes the main direction of development of lifting video monitoring system efficiency.
It is increasing to possess the electronic product of recording function on the market at present, but these electronic product overwhelming majority are required for
Possess and the caching process that video process provides picture is saved as in larger.However, with the compression of electronic product production cost, how
So that product ensures its equal function while production cost is reduced, such as meet picture while memory size is reduced
Caching function, turn into the focus of industry research to improve the competitiveness of electronic product.
The content of the invention
It is an object of the present invention to provide a kind of method for recorded video of classifying, to solve video in the prior art
Video data is not classified effectively during recording, causes the later stage to be searched difficult, the problems such as easy drain message.
Especially, the invention provides a kind of method for recorded video of classifying, for that can be classified record according to surrounding environment
Video processed, including：
S1, record command is received, creates a recorded file in memory, and gather video data, by the video of collection
Data buffer storage is into internal memory random access memory；Wherein, video data is the raw image data captured by camera sensor；
S2, when the video data in the random access memory reaches a preset value, continue to gather video data, wherein,
The residual memory space of the memory is detected, when the residual memory space of the memory reaches preset value, described in traversal
Video data in random access memory, the video data in the random access memory is classified, to the video counts classified
Encoded according to being compressed；
S3, the video data classified is write by recorded file according to preparatory condition respectively.
Alternatively, carrying out classification to video data includes：
According to the luminance mean value of image in video data, the luminance mean curve of the video data is obtained；
Extreme point in the luminance mean curve obtains the indicatrix of the video data；
The video data is classified according to the indicatrix of the video data.
Alternatively, the luminance mean value according to image in video data, the luminance mean value for obtaining the video data are bent
Line includes：
At least one is extracted from the video data according to the duration of the video data and default decimation rule
The video paragraph of individual period；
Row sectional drawing is dropped into each video-frequency band of the extraction；
Calculate the luminance mean value for all images that each video paragraph obtains by sectional drawing；
The luminance mean curve of each video paragraph is obtained respectively, and according to the video paragraph of at least one period
Luminance mean curve obtain the luminance mean curve of the video data.
Alternatively, the described pair of each video-frequency band extracted, which drops into row sectional drawing, includes：It is pre- in the time shaft of video paragraph
If sampling time point annex extract the video image of one or more frame of video as sectional drawing.
Alternatively, the indicatrix according to the video data carries out cluster to the video data includes：
Near video data are searched according to the indicatrix of the video data；
The index information of the video data is established according to the indicatrix of the video data.
Alternatively, by the video data compared with the near video data found, including：
By the indicatrix of the video data compared with the indicatrix of the near video data found；
By the sectional drawing of the video data compared with the sectional drawing of the near video data found.
The method of the recorded video of classifying of the present invention, due to the video data in the random access memory being divided
Class, coding is compressed to the video data classified, therefore can effectively solved because the video data volume is big, searching is got up
The problem of difficult, the rapid drop scope in multitude of video data, find relevant information.
Further, it is of the invention that video data is classified by the luminance mean value of image, can quickly to regarding
Frequency is classified, simple and practical.
According to the accompanying drawings will be brighter to the detailed description of the specific embodiment of the invention, those skilled in the art
Above-mentioned and other purposes, the advantages and features of the present invention.
Brief description of the drawings
Some specific embodiments of the present invention are described in detail by way of example, and not by way of limitation with reference to the accompanying drawings hereinafter.
Identical reference denotes same or similar part or part in accompanying drawing.It should be appreciated by those skilled in the art that these
What accompanying drawing was not necessarily drawn to scale.In accompanying drawing：
Fig. 1 is the indicative flowchart of the method for recorded video according to an embodiment of the invention of classifying.
Embodiment
Fig. 1 is the indicative flowchart of the method for recorded video according to an embodiment of the invention of classifying.Such as Fig. 1 institutes
Show, this method includes：
S1, record command is received, creates a recorded file in memory, and gather video data, by the video of collection
Data buffer storage is into internal memory random access memory；Wherein, video data is the raw image data captured by camera sensor；
S2, when the video data in the random access memory reaches a preset value, continue to gather video data, wherein,
The residual memory space of the memory is detected, when the residual memory space of the memory reaches preset value, described in traversal
Video data in random access memory, the video data in the random access memory is classified, to the video counts classified
Encoded according to being compressed；
S3, the video data classified is write by recorded file according to preparatory condition respectively.
The method of the recorded video of classifying of the present invention, due to the video data in the random access memory being divided
Class, coding is compressed to the video data classified, therefore can effectively solved because the video data volume is big, searching is got up
The problem of difficult, the rapid drop scope in multitude of video data, find relevant information.
In one embodiment of this invention, carrying out classification to video data includes：
According to the luminance mean value of image in video data, the luminance mean curve of the video data is obtained；
Extreme point in the luminance mean curve obtains the indicatrix of the video data；
The video data is classified according to the indicatrix of the video data.
Further, it is of the invention that video data is classified by the luminance mean value of image, can quickly to regarding
Frequency is classified, simple and practical.
In a further embodiment of the invention, the luminance mean value according to image in video data, institute is obtained
Stating the luminance mean curve of video data includes：
At least one is extracted from the video data according to the duration of the video data and default decimation rule
The video paragraph of individual period；
Row sectional drawing is dropped into each video-frequency band of the extraction；
Calculate the luminance mean value for all images that each video paragraph obtains by sectional drawing；
The luminance mean curve of each video paragraph is obtained respectively, and according to the video paragraph of at least one period
Luminance mean curve obtain the luminance mean curve of the video data.
In a still further embodiments of the invention, the described pair of each video-frequency band extracted drops into row sectional drawing bag
Include：Default sampling time point annex extracts the video image conduct of one or more frame of video in the time shaft of video paragraph
Sectional drawing.
In a further embodiment of the invention, the indicatrix according to the video data regards to described
Frequency includes according to cluster is carried out：
Near video data are searched according to the indicatrix of the video data；
The index information of the video data is established according to the indicatrix of the video data.
Alternatively, by the video data compared with the near video data found, including：
By the indicatrix of the video data compared with the indicatrix of the near video data found；
By the sectional drawing of the video data compared with the sectional drawing of the near video data found.
So far, although those skilled in the art will appreciate that detailed herein have shown and described multiple showing for the present invention
Example property embodiment, still, still can be direct according to present disclosure without departing from the spirit and scope of the present invention
It is determined that or derive many other variations or modifications for meeting the principle of the invention.Therefore, the scope of the present invention is understood that and recognized
It is set to and covers other all these variations or modifications.
Claims (6)
1. a kind of method for recorded video of classifying, for that can be classified recorded video according to surrounding environment, it is characterised in that bag
Include：
S1, record command is received, creates a recorded file in memory, and gather video data, by the video data of collection
Caching is into internal memory random access memory；Wherein, video data is the raw image data captured by camera sensor；
S2, when the video data in the random access memory reaches a preset value, continue to gather video data, wherein, detection
The residual memory space of the memory, when the residual memory space of the memory reaches preset value, travel through described random
Video data in holder, the video data in the random access memory is classified, the video data classified is entered
Row compressed encoding；
S3, the video data classified is write by recorded file according to preparatory condition respectively.
2. the method for recorded video according to claim 1 of classifying, it is characterised in that classification bag is carried out to video data
Include：
According to the luminance mean value of image in video data, the luminance mean curve of the video data is obtained；
Extreme point in the luminance mean curve obtains the indicatrix of the video data；
The video data is classified according to the indicatrix of the video data.
3. the method for recorded video according to claim 2 of classifying, it is characterised in that described according to scheming in video data
The luminance mean value of picture, obtaining the luminance mean curve of the video data includes：
When extracting at least one from the video data according to the duration of the video data and default decimation rule
Between section video paragraph；
Row sectional drawing is dropped into each video-frequency band of the extraction；
Calculate the luminance mean value for all images that each video paragraph obtains by sectional drawing；
Obtain the luminance mean curve of each video paragraph respectively, and according to the bright of the video paragraph of at least one period
Spend the luminance mean curve that Mean curve obtains the video data.
4. the method for recorded video according to claim 3 of classifying, it is characterised in that to each video-frequency band extracted
Dropping into row sectional drawing includes：Default sampling time point annex extracts one or more frame of video in the time shaft of video paragraph
Video image is as sectional drawing.
5. the method for recorded video according to claim 4 of classifying, it is characterised in that described according to the video data
Indicatrix cluster carried out to the video data included：
Near video data are searched according to the indicatrix of the video data；
The index information of the video data is established according to the indicatrix of the video data.
6. the method for recorded video according to claim 5 of classifying, it is characterised in that by the video data with it is described
The near video data found are compared, including：
By the indicatrix of the video data compared with the indicatrix of the near video data found；
By the sectional drawing of the video data compared with the sectional drawing of the near video data found.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710980630.3A CN107707857A (en) | 2017-10-19 | 2017-10-19 | A kind of method for recorded video of classifying |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710980630.3A CN107707857A (en) | 2017-10-19 | 2017-10-19 | A kind of method for recorded video of classifying |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107707857A true CN107707857A (en) | 2018-02-16 |
Family
ID=61181787
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710980630.3A Pending CN107707857A (en) | 2017-10-19 | 2017-10-19 | A kind of method for recorded video of classifying |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107707857A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1295759A (en) * | 1998-07-01 | 2001-05-16 | 株式会社日立制作所 | Recorded program viewing support method |
| US20040117230A1 (en) * | 2002-12-16 | 2004-06-17 | Jones Kevin Thomas | Recalculating planned requests |
| CN101794515A (en) * | 2010-03-29 | 2010-08-04 | 河海大学 | Target detection system and method based on covariance and binary-tree support vector machine |
| CN202617281U (en) * | 2012-06-02 | 2012-12-19 | 上海大学 | Intelligent monitoring system for massive video data |
| CN103297739A (en) * | 2012-02-22 | 2013-09-11 | 安凯(广州)微电子技术有限公司 | Method and device for recording audio and video |
| CN103631786A (en) * | 2012-08-22 | 2014-03-12 | 腾讯科技（深圳）有限公司 | Clustering method and device for video files |
-
2017
- 2017-10-19 CN CN201710980630.3A patent/CN107707857A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1295759A (en) * | 1998-07-01 | 2001-05-16 | 株式会社日立制作所 | Recorded program viewing support method |
| US20040117230A1 (en) * | 2002-12-16 | 2004-06-17 | Jones Kevin Thomas | Recalculating planned requests |
| CN101794515A (en) * | 2010-03-29 | 2010-08-04 | 河海大学 | Target detection system and method based on covariance and binary-tree support vector machine |
| CN103297739A (en) * | 2012-02-22 | 2013-09-11 | 安凯(广州)微电子技术有限公司 | Method and device for recording audio and video |
| CN202617281U (en) * | 2012-06-02 | 2012-12-19 | 上海大学 | Intelligent monitoring system for massive video data |
| CN103631786A (en) * | 2012-08-22 | 2014-03-12 | 腾讯科技（深圳）有限公司 | Clustering method and device for video files |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10345046B2 (en) | Fault diagnosis device based on common information and special information of running video information for electric-arc furnace and method thereof | |
| Pegoraro et al. | Automated video monitoring of insect pollinators in the field | |
| CN109766779B (en) | Loitering person identification method and related product | |
| US20210357678A1 (en) | Information processing method and apparatus, and storage medium | |
| US8566314B2 (en) | System and related techniques for detecting and classifying features within data | |
| EP3082065A1 (en) | Duplicate reduction for face detection | |
| CN102930261A (en) | Face snapshot recognition method | |
| WO2020094088A1 (en) | Image capturing method, monitoring camera, and monitoring system | |
| CN103347167A (en) | Surveillance video content description method based on fragments | |
| CN108416256A (en) | The family's cloud intelligent monitor system and monitoring method of feature based identification | |
| CN102665071A (en) | Intelligent processing and search method for social security video monitoring images | |
| US20150085114A1 (en) | Method for Displaying Video Data on a Personal Device | |
| CN105718871A (en) | Video host identification method based on statistics | |
| CN110096945B (en) | Indoor monitoring video key frame real-time extraction method based on machine learning | |
| CN104091175B (en) | A kind of insect automatic distinguishing method for image based on Kinect depth information acquiring technology | |
| CN102193918A (en) | Video retrieval method and device | |
| CN108898098A (en) | Early stage video smoke detection method based on monitor supervision platform | |
| CN102831166A (en) | Criminal investigation video preprocessing method based on color feature detection | |
| CN113343779A (en) | Environment anomaly detection method and device, computer equipment and storage medium | |
| WO2018223960A1 (en) | Method, device, system, electronic terminal, and readable storage medium for processing surveillance video | |
| CN116419059A (en) | Automatic monitoring method, device, equipment and medium based on behavior label | |
| CN109583414B (en) | Indoor road occupation detection method, device, medium and processor based on video detection | |
| KR101547255B1 (en) | Object-based Searching Method for Intelligent Surveillance System | |
| CN102331988A (en) | Pornography image and video filtering and identifying system based on content mining and feature identification | |
| CN104270619B (en) | A kind of security alarm method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180216 |
|
| RJ01 | Rejection of invention patent application after publication |