CN107025292A - The description method of video and heterogeneous sensor in towards transformer station - Google Patents
The description method of video and heterogeneous sensor in towards transformer station Download PDFInfo
- Publication number
- CN107025292A CN107025292A CN201710242861.4A CN201710242861A CN107025292A CN 107025292 A CN107025292 A CN 107025292A CN 201710242861 A CN201710242861 A CN 201710242861A CN 107025292 A CN107025292 A CN 107025292A
- Authority
- CN
- China
- Prior art keywords
- description
- information
- video
- layer
- transformer station
- 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
-
- 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
- G06F16/71—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
Abstract
The present invention relates to a kind of description method towards video in transformer station and heterogeneous sensor, it is characterized in that, it is specific as follows using hierarchical description：First layer is acquired to heat transfer agent, and sensing data is pre-processed, and extracts characteristic value；The temporal information that the second layer is associated according to heat transfer agent, the video information to synchronization carries out the physical attribute description of original image；Third layer is converted images into as logical relation, and associated sensor data carry out Unify legislation；4th layer represented from image, object and association heat transfer agent in take out semantic attribute, and the semanteme changed from logical relation, obtain structural description symbol.The present invention can realize the structuring of heterogeneous sensor data, facilitate coding and the transmission of integrated information, improve information processing and effectiveness of retrieval, make retrieval result more accurate.
Description
Technical field
Method is described the present invention relates to a kind of video mix sensing data, it is especially a kind of towards video in transformer station with it is different
The description method of structure sensor, belongs to video presentation technical field.
Background technology
Video information has obtained the extensive use of all trades and professions, such as bank, business to provide abundant and lively information
Field, supermarket, the intensive traffic section, cell crossing etc..For the operation conditions of clear and intuitive monitoring visual plant inside transformer station, also all
Video monitoring is mounted with, but video monitoring only provides image/video information, can not but carry out early warning, can be equipment fault
Leave and often install other sensing equipments in videograph, therefore transformer station additional.But it is due to that sensing equipment and video monitoring are adhered to separately
Different manufacturers, are presently mainly that video data and other sensors data are respectively stored into database, it is impossible to unified
Data transfer and storage.
Video data often has that data volume is big, temporal and spatial correlations degree is high and description, it is difficult to traditional
Data model is described.Use the coded system of object-oriented more current video, and concentrate in content and information in itself,
Compression, coding and expression such as to video and voice data, and sensing data is individually stored in database, it is impossible to carry out comprehensive
The analysis of conjunction, it is necessary to when need individually to be compared.
How the sensing datas such as video information and temperature, vibration to be combined, using the description of structuring, all the time
It is a problem.
The content of the invention
The purpose of the present invention is to overcome the deficiencies in the prior art there is provided one kind towards video in transformer station and isomery
The description method of sensor, realizes the structuring of heterogeneous sensor data, facilitates coding and the transmission of integrated information, improves
Information processing and effectiveness of retrieval, make retrieval result more accurate.
The technical scheme provided according to the present invention, it is a kind of towards video in transformer station and the structural description of heterogeneous sensor
Method, it is characterized in that, it is specific as follows using hierarchical description：
First layer is acquired to heat transfer agent, and sensing data is pre-processed, and extracts characteristic value；
The temporal information that the second layer is associated according to heat transfer agent, the video information to synchronization carries out the physics category of original image
Property description；
Third layer is converted images into as logical relation, and associated sensor data carry out Unify legislation；
4th layer represented from image, object and association heat transfer agent in take out semantic attribute, and from logical relation transfer
The semanteme changed, obtains structural description symbol.
Further, the physical attribute description of the second layer video information is described according to video-frequency band, extracts per frame
The characteristic information of image.
Further, the physical attribute description of the second layer video information includes colouring information, profile information, texture letter
Breath, movable information, acoustic information and energy information.
Further, the structural description symbol is mainly used in describing following information type：Object factory, sensing association letter
Cease description, relationship description, movement relation description and operation maintenance personnel description.
Further, the operation maintenance personnel description mainly describes following information type：Personnel's description, location expression and relation
Description.
Further, the first layer sensing data adds timestamp after being pre-processed.
Further, the heat transfer agent includes temperature information, noise information and partial discharge information.
Further, the precondition of the structural description is that video monitoring system and Internet of things system have been pressed
It is synchronous according to the UTC unified time reference hierarchy deadlines.
Description method of the present invention towards video in transformer station and heterogeneous sensor, can be by video information
With heterogeneous sensor information integrate associating description, facilitate uniform transmission, storage, and improve the speed of transmission, also cause the later stage
Retrieval is more efficient.
Brief description of the drawings
Fig. 1 is the flow chart of the structural description of video of the present invention and heterogeneous sensor.
Fig. 2 is the schematic diagram of the structural description model of video of the present invention and heterogeneous sensor.
Embodiment
With reference to specific accompanying drawing, the invention will be further described.
Untreated video data is non-structured data, and currently used information description method mainly passes through figure
A complete semantic concept is showed as, sound and text, only object-oriented is described, it is impossible to incorporate environmental information
Wherein, demand can not be met, by being combined with sensing data, the multi-angle information description at same time point is may be constructed,
Facilitate stored in association, transmission and retrieval.
It is of the present invention towards video in transformer station and the precondition of the description method of heterogeneous sensor, video
Monitoring system and Internet of things system are synchronous according to the UTC unified time reference hierarchy deadlines, are carried out using descriptor
The description at same time point, so as to realize that the sensor informations such as video information and GPS, infrared temperature, partial discharge are associated, is improved
The exchangeability of data and the uniformity of data management, reduce redundancy, can quickly carry out data transmission, and using less
Memory space.Schematic flow sheet is as shown in Figure 1.
As shown in figure 1, heretofore described description method is mainly as follows：
Description information is divided into two major classes：Belong to the description information of video and belong to the description information of sensor；Video presentation
It is described according to video-frequency band, extracts the characteristic information and semantic layer analysis per two field picture；Sensing data by pretreatment,
Characteristic value is extracted, semantic layer analysis is built.The information of video bottom is unrelated with object：Mainly temporal information, format information, wound
Build information and characteristic information；The key frame of frame of video is mainly described by color, texture, motion etc.；Structural description is accorded with
It is mainly used in describing following information type：Object factory, sensing related information description, relationship description, movement relation describe and
Operation maintenance personnel is described.Operation maintenance personnel description mainly describes following information type：Personnel's description, location expression and relationship description.Enter
Row hierarchical description, improves the exchangeability of data and the uniformity of data management, is easy to inquire about by iterative process, and then can be high
The inquiry of effect ground.
As shown in Fig. 2 entering for the description method of the present invention towards video in transformer station and heterogeneous sensor
The model of row hierarchical description：First layer is that the heat transfer agents such as such as temperature, noise, partial discharge are acquired, and carries out letter to data
Single pretreatment, because the change of sensing data is slow, by recording changing value, it is possible to reduce stored memory, and will pretreatment
Information addition timestamp, and statistical nature, addition feature and text annotation；The second layer is the time associated according to heat transfer agent
Information, the mainly video information to synchronization carry out regarding for the physical attribute description of original image, i.e. image objective reality
Feel the property that can be distinguished, such as color, profile, texture, motion, sound, energy physical features are described；Third layer is
Convert images into as logical relation, and associate sensing data and carry out Unify legislation, profile information, the temperature letter of such as transformer tank
Breath, the isallobaric device case related information of noise information, the breaker such as profile information, temperature information, the SF6 breaker informations of breaker
Related information；4th layer is to take out semantic attribute, such as transformer in being represented from image, object and association heat transfer agent
Case is normal, its general property, and the semanteme changed from logical construction.
The present invention is the method that video information and heat transfer agent are described, the description of prior art video information and sensing
Data message description belongs to two completely self-contained systems, and the present invention enters the video camera and the data of sensor inside transformer station
The unified description of row, is convenient for unified coding and subsequent transmission, improves information processing and effectiveness of retrieval, make retrieval result
It is more accurate.
Claims (8)
1. a kind of description method towards video in transformer station and heterogeneous sensor, it is characterized in that, using hierarchical description,
It is specific as follows：
First layer is acquired to heat transfer agent, and sensing data is pre-processed, and extracts characteristic value；
The temporal information that the second layer is associated according to heat transfer agent, the video information to synchronization carries out the physics category of original image
Property description；
Third layer is converted images into as logical relation, and associated sensor data carry out Unify legislation；
4th layer represented from image, object and association heat transfer agent in take out semantic attribute, and from logical relation transfer
The semanteme changed, obtains structural description symbol.
2. the description method as claimed in claim 1 towards video in transformer station and heterogeneous sensor, it is characterized in that：
The physical attribute description of the second layer video information is described according to video-frequency band, extracts the characteristic information per two field picture.
3. the description method as claimed in claim 1 or 2 towards video in transformer station and heterogeneous sensor, its feature
It is：The physical attribute description of the second layer video information includes colouring information, profile information, texture information, movable information, sound
Message ceases and energy information.
4. the description method as claimed in claim 1 towards video in transformer station and heterogeneous sensor, it is characterized in that：
The structural description symbol is mainly used in describing following information type：Object factory, sensing related information description, relationship description,
Movement relation is described and operation maintenance personnel description.
5. the description method as claimed in claim 4 towards video in transformer station and heterogeneous sensor, it is characterized in that：
The operation maintenance personnel description mainly describes following information type：Personnel's description, location expression and relationship description.
6. the description method as claimed in claim 1 towards video in transformer station and heterogeneous sensor, it is characterized in that：
The first layer sensing data adds timestamp after being pre-processed.
7. the description method as claimed in claim 1 towards video in transformer station and heterogeneous sensor, it is characterized in that：
The heat transfer agent includes temperature information, noise information and partial discharge information.
8. the description method as claimed in claim 1 towards video in transformer station and heterogeneous sensor, it is characterized in that：
The precondition of the structural description is that video monitoring system and Internet of things system have been referred to according to UTC unified times
The system deadline is synchronous.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710242861.4A CN107025292A (en) | 2017-04-14 | 2017-04-14 | The description method of video and heterogeneous sensor in towards transformer station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710242861.4A CN107025292A (en) | 2017-04-14 | 2017-04-14 | The description method of video and heterogeneous sensor in towards transformer station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107025292A true CN107025292A (en) | 2017-08-08 |
Family
ID=59527862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710242861.4A Pending CN107025292A (en) | 2017-04-14 | 2017-04-14 | The description method of video and heterogeneous sensor in towards transformer station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107025292A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107831409A (en) * | 2017-09-22 | 2018-03-23 | 国网山东省电力公司电力科学研究院 | The method and method for detecting abnormality of superfrequency partial discharge detection TuPu method parameter extraction |
| CN110998245A (en) * | 2017-08-09 | 2020-04-10 | 欧姆龙株式会社 | Sensor management unit, sensor device, sensor management method, and sensor management program |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102348101A (en) * | 2010-07-30 | 2012-02-08 | 深圳市先进智能技术研究所 | Examination room intelligence monitoring system and method thereof |
| CN103248703A (en) * | 2013-05-16 | 2013-08-14 | 中国农业大学 | Automatic monitoring system and method for live pig action |
| US20140082002A1 (en) * | 2012-09-20 | 2014-03-20 | Electronics And Telecommunications Research Institute | Apparatus and method for processing unstructured data event in real time |
| CN104767974A (en) * | 2015-04-09 | 2015-07-08 | 合肥三立自动化工程有限公司 | Intelligent remote monitoring terminal with video monitoring function and control method thereof |
| CN104899261A (en) * | 2015-05-20 | 2015-09-09 | 杜晓通 | Device and method for constructing structured video image information |
| CN105847752A (en) * | 2016-04-22 | 2016-08-10 | 广东中星电子有限公司 | Information encoding and decoding method, equipment and video monitoring system |
| CN106355811A (en) * | 2016-07-22 | 2017-01-25 | 河南城建学院 | Electrical fire monitoring system |
| CN106485412A (en) * | 2016-09-30 | 2017-03-08 | 国网江苏省电力公司电力科学研究院 | A kind of transformer station image intelligent level of analysis multiple task distributive computational methods |
-
2017
- 2017-04-14 CN CN201710242861.4A patent/CN107025292A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102348101A (en) * | 2010-07-30 | 2012-02-08 | 深圳市先进智能技术研究所 | Examination room intelligence monitoring system and method thereof |
| US20140082002A1 (en) * | 2012-09-20 | 2014-03-20 | Electronics And Telecommunications Research Institute | Apparatus and method for processing unstructured data event in real time |
| CN103248703A (en) * | 2013-05-16 | 2013-08-14 | 中国农业大学 | Automatic monitoring system and method for live pig action |
| CN104767974A (en) * | 2015-04-09 | 2015-07-08 | 合肥三立自动化工程有限公司 | Intelligent remote monitoring terminal with video monitoring function and control method thereof |
| CN104899261A (en) * | 2015-05-20 | 2015-09-09 | 杜晓通 | Device and method for constructing structured video image information |
| CN105847752A (en) * | 2016-04-22 | 2016-08-10 | 广东中星电子有限公司 | Information encoding and decoding method, equipment and video monitoring system |
| CN106355811A (en) * | 2016-07-22 | 2017-01-25 | 河南城建学院 | Electrical fire monitoring system |
| CN106485412A (en) * | 2016-09-30 | 2017-03-08 | 国网江苏省电力公司电力科学研究院 | A kind of transformer station image intelligent level of analysis multiple task distributive computational methods |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110998245A (en) * | 2017-08-09 | 2020-04-10 | 欧姆龙株式会社 | Sensor management unit, sensor device, sensor management method, and sensor management program |
| CN107831409A (en) * | 2017-09-22 | 2018-03-23 | 国网山东省电力公司电力科学研究院 | The method and method for detecting abnormality of superfrequency partial discharge detection TuPu method parameter extraction |
| CN107831409B (en) * | 2017-09-22 | 2020-08-18 | 国网山东省电力公司电力科学研究院 | Ultrahigh frequency partial discharge detection map characteristic parameter extraction method and anomaly detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20180007429A1 (en) | Intelligent processing method and system for video data | |
| US9053194B2 (en) | Method and apparatus for correlating and viewing disparate data | |
| CN105574133A (en) | Multi-mode intelligent question answering system and method | |
| CN106487891B (en) | A method of the processing message based on kafka | |
| CN112001184B (en) | User emotion difference region detection method and system for video bullet screen | |
| CN103902718A (en) | Report control and application thereof | |
| CN104298748A (en) | Device and method for face search in videos | |
| WO2022116545A1 (en) | Interaction method and apparatus based on multi-feature recognition, and computer device | |
| CN107025292A (en) | The description method of video and heterogeneous sensor in towards transformer station | |
| CN110932405A (en) | Intelligent monitoring and analyzing system for power transformation equipment based on big data | |
| CN114723904A (en) | Method, system, computer device and storage medium for dynamic management of airport data | |
| CN111709928A (en) | Video-based near-shore wave height real-time detection system | |
| CN109977856B (en) | Method for identifying complex behaviors in multi-source video | |
| CN201414197Y (en) | Miscs intelligent monitoring system | |
| CN116010652B (en) | Unstructured video data processing method and system | |
| CN103383649A (en) | Design model of complex virtual instrument system | |
| CN116977992A (en) | Text information identification method, apparatus, computer device and storage medium | |
| Sun et al. | Cdva/vcm: Language for intelligent and autonomous vehicles | |
| Xu et al. | Video structural description: a semantic based model for representing and organizing video surveillance big data | |
| Park et al. | Deep-Learning Based Real-time Fire Detection Using Object Tracking Algorithm | |
| CN108595469A (en) | A kind of semantic-based agricultural machinery monitor video image section band Transmission system | |
| CN204102129U (en) | A kind of device for face retrieval in video | |
| CN116340550A (en) | Text label determining method and related device | |
| Wang | Video description with GAN | |
| Li et al. | Improved YOLOV3 Surveillance Device Object Detection Method Based on Federated Learning |
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: 20170808 |
|
| RJ01 | Rejection of invention patent application after publication |