CN106339484A - System and method for intelligent video retrieval processing - Google Patents
System and method for intelligent video retrieval processing Download PDFInfo
- Publication number
- CN106339484A CN106339484A CN201610782666.6A CN201610782666A CN106339484A CN 106339484 A CN106339484 A CN 106339484A CN 201610782666 A CN201610782666 A CN 201610782666A CN 106339484 A CN106339484 A CN 106339484A
- Authority
- CN
- China
- Prior art keywords
- video
- video file
- retrieval
- file
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention relates to a system and a method for intelligent video retrieval processing. The system comprises a management module, a storage module and an analysis module, wherein the management module is used for managing an uploading task of a video file and assigning a video retrieval and analysis task; the storage module is used for receiving the uploaded video file, transcoding the video file so as to generate a file in a standard format, storing the file, and sharing the video file with the analysis module; the analysis module is used for quantifying the video file, storing the quantified video file, retrieving according to the quantified video file, and storing a retrieved result. The system and the method provided by the invention have the advantages that time consumed for analyzing the video in video retrieval is reduced, personnel handling a case can conveniently and quickly retrieve and position a target, a source video file can be prevented from being decoded and analyzed again, and the waste of server resources is prevented.
Description
Technical field
The present invention relates to intelligent security guard field, in particular, it is to be related to a kind of system to video intelligent retrieval process
And method.
Background technology
Video intelligent retrieval can find out more similar target according to clue feature in a large amount of moving targets, greatly improves
The efficiency handled a case.It has become as an indispensable investigation in intelligent security guard field at present, and wherein cross-line is trans-regional
Detection, color are retrieved, to scheme to search the common technologies such as figure, in actual applications widely.With the popularization of current supervision of the cities,
Blowout and increases in video, and video is carried out with effectiveness of retrieval and requires also more and more higher.When retrieval technique day by day maturation,
Its efficiency usually becomes a very important criterion of video frequency searching quality.
Content of the invention
In view of this it is necessary to be directed to the problems referred to above, a kind of system and method to video intelligent retrieval process is provided, subtracts
In few video frequency searching, spent time is analyzed to video, facilitates personnel in charge of the case's quick-searching and position target, and be avoided that
Again source video file decoding is analyzed, cause the waste of server resource.
To achieve these goals, technical scheme is as follows:
Fig. 1 shows a kind of system of video intelligent retrieval process, including management module, memory module and analysis module,
Described management module is used for managing the upload task of video file and distribution video frequency searching, analysis task;Described memory module is used
Stored in the file receiving the video file uploading transcoding generation reference format, and video file is shared to analysis mould
Block;Described analysis module is used for video file quantification treatment and stores, and enters line retrieval and deposits according to the video file after quantifying
Storage retrieval result.
As preferred, described memory module includes file reception memory cell and transcoding units, and described file reception is deposited
Storage unit is used for the former video file needing analysis is carried out receiving to preserve, and described transcoding units are used for the video receiving literary composition
Part is transcoded into the video file of reference format.
As preferred, described analysis module includes pretreatment unit and retrieval unit, and it is right that described pretreatment unit is used for
Video file is decoded and analyzes, and by the data after analysis and in order to the view data analyzed according to one-to-one principle
Quantify and store;The Rule Information that described retrieval unit is used in the retrieval tasks getting carries out the trans-regional retrieval of cross-line, face
Color is retrieved or to scheme to search figure, enters line retrieval screening according to specified rule to the file after processing, and stores the letter after screening
Breath.
As preferred, described analysis module also includes accelerating scheduling unit, and described acceleration scheduling unit is used for place
The load of gpu and cpu of server carries out real-time detection and scheduling, with server combination property as reference index, according to video
Solution bit rate and decoding after the quantization speed of view data is compared to both sides actual conditions, processing data is relatively slow
A side then utilize gpu accelerate.It is slow compared with causing the speed retrieved slowly that wherein one side's processing speed so can be prevented, it is to avoid cpu
Or gpu load that the uneven server performance causing is unbalance and resource idle, thus lifted searching system whole efficiency and
Server resource utilization rate.
Fig. 2 shows the method carrying out video intelligent retrieval process according to said system always, comprises the following steps:
S1, management module issue retrieval tasks to pretreatment unit;
S2, pretreatment unit obtain former video file from memory module;
S3, inquire about the whether pretreated mistake of this video file from database;
If s4 video file is processed, enter step s5, if video file is not processed, according to cpu's and gpu
Load and the operational capability dispatch deal that video is decoded and analyzes, the data of the data of decoding and analysis is saved in
The position specified, the unique number of corresponding video;
S5, according to retrieval rule to pretreatment data screen, obtain result and store.
Compared with prior art, the beneficial effects of the present invention is:
1. reduce in video frequency searching and spent time is analyzed to video, facilitate personnel in charge of the case's quick-searching and position mesh
Mark;
2. two times or repeatedly retrieve when, be avoided that again to source video file decoding analyze, cause the wave of server resource
Take.
Brief description
Fig. 1 is embodiment of the present invention system architecture diagram
Fig. 2 is present invention method flow chart.
Specific embodiment
With reference to the accompanying drawings and examples to a kind of system and method to video intelligent retrieval process of the present invention
It is described further.
The following is a kind of preferred example of system and method to video intelligent retrieval process of the present invention, not because
This limits protection scope of the present invention.
A kind of system of video intelligent retrieval process, including management module, memory module and analysis module, described management mould
Block is used for managing the upload task of video file and distribution video frequency searching, analysis task;Described memory module is used for receiving upload
Video file and transcoding generate the file of reference format and stored, and video file is shared to analysis module;Described point
Analysis module is used for video file quantification treatment and stores, and enters line retrieval memory scan knot according to the video file after quantifying
Really.
As preferred, described memory module includes file reception memory cell and transcoding units, and described file reception is deposited
Storage unit is used for the former video file needing analysis is carried out receiving to preserve, and described transcoding units are used for the video receiving literary composition
Part is transcoded into the video file of reference format.
As preferred, described analysis module includes pretreatment unit and retrieval unit, and it is right that described pretreatment unit is used for
Video file is decoded and analyzes, and by the data after analysis and in order to the view data analyzed according to one-to-one principle
Quantify and store;The Rule Information that described retrieval unit is used in the retrieval tasks getting carries out the trans-regional retrieval of cross-line, face
Color is retrieved or to scheme to search figure, enters line retrieval screening according to specified rule to the file after processing, and stores the letter after screening
Breath.
As preferred, described analysis module also includes accelerating scheduling unit, and described acceleration scheduling unit is used for place
The load of gpu and cpu of server carries out real-time detection and scheduling, with server combination property as reference index, according to video
Solution bit rate and decoding after the quantization speed of view data is compared to both sides actual conditions, processing data is relatively slow
A side then utilize gpu accelerate.It is slow compared with causing the speed retrieved slowly that wherein one side's processing speed so can be prevented, it is to avoid cpu
Or gpu load that the uneven server performance causing is unbalance and resource idle, thus lifted searching system whole efficiency and
Server resource utilization rate.
The method carrying out video intelligent retrieval process according to said system always, comprises the following steps:
S1, management module issue retrieval tasks to pretreatment unit;
S2, pretreatment unit obtain former video file from memory module;
S3, inquire about the whether pretreated mistake of this video file from database;
If s4 video file is processed, enter step s5, if video file is not processed, according to cpu's and gpu
Load and the operational capability dispatch deal that video is decoded and analyzes, the data of the data of decoding and analysis is saved in
The position specified, the unique number of corresponding video;
S5, according to retrieval rule to pretreatment data screen, obtain result and store, retrieval unit is to previous
The pretreatment information of secondary preservation screened, it is to avoid expend big when during secondary or multiple retrieval to video decoding or gathered data
Amount time and occupancy server resource.
Compared with prior art, the beneficial effects of the present invention is:
1. reduce in video frequency searching and spent time is analyzed to video, facilitate personnel in charge of the case's quick-searching and position mesh
Mark;
2. two times or repeatedly retrieve when, be avoided that again to source video file decoding analyze, cause the wave of server resource
Take.
Embodiment described above only have expressed the several embodiments of the present invention, and its description is more concrete and detailed, but simultaneously
Therefore the restriction to the scope of the claims of the present invention can not be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, some deformation can also be made and improve, these broadly fall into the guarantor of the present invention
Shield scope.Therefore, the protection domain of patent of the present invention should be defined by claims.
Claims (5)
1. a kind of system of video intelligent retrieval process is it is characterised in that include management module, memory module and analysis module,
Described management module is used for managing the upload task of video file and distribution video frequency searching, analysis task;Described memory module is used
Stored in the file receiving the video file uploading transcoding generation reference format, and video file is shared to analysis mould
Block;Described analysis module is used for video file quantification treatment and stores, and enters line retrieval and deposits according to the video file after quantifying
Storage retrieval result.
2. the system of video intelligent retrieval process according to claim 1 is it is characterised in that described memory module includes literary composition
Part receives memory cell and transcoding units, and described file reception memory cell is used for the former video file needing analysis is connect
Receive and preserve, described transcoding units are used for the video file receiving is transcoded into the video file of reference format.
3. video intelligent retrieval process according to claim 1 system it is characterised in that described analysis module include pre-
Processing unit and retrieval unit, described pretreatment unit is used for video file being decoded and analyzing, and by the number after analysis
According to quantifying according to one-to-one principle with the view data in order to analyze and store;Described retrieval unit is used for the inspection getting
Rule Information in rope task carries out the trans-regional retrieval of cross-line, color is retrieved or to scheme to search figure, according to specified rule to place
File after reason enters line retrieval screening, and stores the information after screening.
4. the system of video intelligent retrieval process according to claim 3 is it is characterised in that described analysis module also includes
Accelerate scheduling unit, the load that described acceleration scheduling unit is used for gpu and cpu to place server carries out real-time detection and tune
Degree, with server combination property as reference index, solution bit rate according to video and the quantization speed to view data after decoding
Both sides actual conditions are compared, the relatively slow side of processing data then utilizes gpu to accelerate.
5. the method for video intelligent retrieval process is carried out it is characterised in that wrapping according to the arbitrary described system of Claims 1-4
Include following steps:
S1, management module issue retrieval tasks to pretreatment unit;
S2, pretreatment unit obtain former video file from memory module;
S3, inquire about the whether pretreated mistake of this video file from database;
If s4 video file is processed, enter step s5, if video file is not processed, according to the load of cpu and gpu
And the dispatch deal that operational capability is decoded to video and analyzes, the data of the data of decoding and analysis is saved in specified
Position, the unique number of corresponding video;
S5, according to retrieval rule to pretreatment data screen, obtain result and store.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610782666.6A CN106339484B (en) | 2016-08-31 | 2016-08-31 | A kind of system and method for video intelligent retrieval process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610782666.6A CN106339484B (en) | 2016-08-31 | 2016-08-31 | A kind of system and method for video intelligent retrieval process |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106339484A true CN106339484A (en) | 2017-01-18 |
CN106339484B CN106339484B (en) | 2019-07-12 |
Family
ID=57823513
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610782666.6A Active CN106339484B (en) | 2016-08-31 | 2016-08-31 | A kind of system and method for video intelligent retrieval process |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106339484B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106844654A (en) * | 2017-01-23 | 2017-06-13 | 公安部第三研究所 | Towards the massive video distributed search method of police service practical |
CN108763437A (en) * | 2018-05-25 | 2018-11-06 | 广州钱柜软件科技有限公司 | A kind of video storage tube reason system based on big data |
CN109190584A (en) * | 2018-09-18 | 2019-01-11 | 银河水滴科技(北京)有限公司 | A kind of portable video searching system |
CN109408667A (en) * | 2018-09-18 | 2019-03-01 | 银河水滴科技(北京)有限公司 | A kind of video frequency search system |
CN110598048A (en) * | 2018-05-25 | 2019-12-20 | 北京中科寒武纪科技有限公司 | Video retrieval method and video retrieval mapping relation generation method and device |
CN111460217A (en) * | 2020-03-31 | 2020-07-28 | 苏州科达科技股份有限公司 | Video retrieval system and method for operating a video retrieval system |
CN112541390A (en) * | 2020-10-30 | 2021-03-23 | 四川天翼网络服务有限公司 | Frame-extracting dynamic scheduling method and system for violation analysis of examination video |
US11995556B2 (en) | 2018-05-18 | 2024-05-28 | Cambricon Technologies Corporation Limited | Video retrieval method, and method and apparatus for generating video retrieval mapping relationship |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103258028A (en) * | 2013-05-08 | 2013-08-21 | 林凡 | Video hierarchical and partitioned storage system based on content features |
CN103713949A (en) * | 2012-10-09 | 2014-04-09 | 鸿富锦精密工业(深圳)有限公司 | System and method for dynamic task allocation |
CN104252539A (en) * | 2014-09-24 | 2014-12-31 | 深圳市傲天智能系统有限公司 | Intelligent video analysis and management method and system based on search engine |
CN105225683A (en) * | 2014-06-18 | 2016-01-06 | 中兴通讯股份有限公司 | Audio frequency playing method and device |
-
2016
- 2016-08-31 CN CN201610782666.6A patent/CN106339484B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103713949A (en) * | 2012-10-09 | 2014-04-09 | 鸿富锦精密工业(深圳)有限公司 | System and method for dynamic task allocation |
CN103258028A (en) * | 2013-05-08 | 2013-08-21 | 林凡 | Video hierarchical and partitioned storage system based on content features |
CN105225683A (en) * | 2014-06-18 | 2016-01-06 | 中兴通讯股份有限公司 | Audio frequency playing method and device |
CN104252539A (en) * | 2014-09-24 | 2014-12-31 | 深圳市傲天智能系统有限公司 | Intelligent video analysis and management method and system based on search engine |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106844654A (en) * | 2017-01-23 | 2017-06-13 | 公安部第三研究所 | Towards the massive video distributed search method of police service practical |
US11995556B2 (en) | 2018-05-18 | 2024-05-28 | Cambricon Technologies Corporation Limited | Video retrieval method, and method and apparatus for generating video retrieval mapping relationship |
CN108763437A (en) * | 2018-05-25 | 2018-11-06 | 广州钱柜软件科技有限公司 | A kind of video storage tube reason system based on big data |
CN110598048A (en) * | 2018-05-25 | 2019-12-20 | 北京中科寒武纪科技有限公司 | Video retrieval method and video retrieval mapping relation generation method and device |
CN110598048B (en) * | 2018-05-25 | 2021-01-29 | 中科寒武纪科技股份有限公司 | Video retrieval method and video retrieval mapping relation generation method and device |
CN109190584A (en) * | 2018-09-18 | 2019-01-11 | 银河水滴科技(北京)有限公司 | A kind of portable video searching system |
CN109408667A (en) * | 2018-09-18 | 2019-03-01 | 银河水滴科技(北京)有限公司 | A kind of video frequency search system |
CN111460217A (en) * | 2020-03-31 | 2020-07-28 | 苏州科达科技股份有限公司 | Video retrieval system and method for operating a video retrieval system |
CN112541390A (en) * | 2020-10-30 | 2021-03-23 | 四川天翼网络服务有限公司 | Frame-extracting dynamic scheduling method and system for violation analysis of examination video |
CN112541390B (en) * | 2020-10-30 | 2023-04-25 | 四川天翼网络股份有限公司 | Frame extraction dynamic scheduling method and system for examination video violation analysis |
Also Published As
Publication number | Publication date |
---|---|
CN106339484B (en) | 2019-07-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106339484A (en) | System and method for intelligent video retrieval processing | |
CN111177095B (en) | Log analysis method, device, computer equipment and storage medium | |
Tan et al. | An approach for fast and parallel video processing on Apache Hadoop clusters | |
CN109769115A (en) | A kind of method, apparatus and equipment of Intelligent Optimal video analysis performance | |
CN107517131A (en) | A kind of analysis and early warning method based on log collection | |
CN111046022A (en) | Database auditing method based on big data technology | |
CN112084224B (en) | Data management method, system, equipment and medium | |
CN111523527B (en) | Special transport vehicle monitoring method and device, medium and electronic equipment | |
CN104252539A (en) | Intelligent video analysis and management method and system based on search engine | |
CN109301936B (en) | Intelligent substation operation and maintenance information monitoring system based on container scheduling framework | |
CN105138676A (en) | Sub-library and sub-table merge query method based on high-level language concurrent aggregation calculation | |
CN106257447A (en) | The video storage of cloud storage server and search method, video cloud storage system | |
CN102609314A (en) | Quantification management method and quantification management system for virtual machine | |
CN112534399A (en) | Semantic-based Internet of things equipment data processing related application program installation method and device | |
CN110661999A (en) | Video monitoring system based on big data | |
CN107204892B (en) | Power communication network operation data processing method and device | |
CN110134578A (en) | A kind of data processing method and device | |
CN106485412B (en) | A kind of substation's image intelligent level of analysis multiple task distributive calculation method | |
CN103970605A (en) | Low-performance terminal based data analysis method and device | |
CN111796993B (en) | Data processing method and device, electronic equipment and computer readable storage medium | |
CN115344455A (en) | Log processing method and device, electronic equipment and storage medium | |
CN109597795B (en) | High-efficiency processing system for roadbed compaction construction data | |
CN110688504B (en) | Image data management method, apparatus, system, device and medium | |
CN110209853B (en) | Image searching method, device and equipment for vehicle | |
CN113918636A (en) | ETL-based data throughput analysis method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |